1. A hotel customer service method based on a knowledge base is characterized by comprising the following steps:

monitoring the communication state of a customer service end and a question of a user end in real time in the communication process of the customer service end and the user end;

when the call state meets a trigger condition, searching whether a question with the similarity degree larger than a similarity degree threshold value to the question exists in an intelligent knowledge base of the current hotel;

if yes, pushing the answer of the question corresponding to the searched maximum similarity to the customer service end;

if not, searching answers of the questions matched with the question questions from the standby knowledge base of the current hotel, and pushing the answers to the customer service end.

2. The hotel customer service method of claim 1, wherein the triggering condition is:

the customer service end inputs a query statement corresponding to the question; or

The duration of the voice-off, the pause duration or the repetition frequency of the useless words in the continuous voice of the customer service end exceeds the corresponding threshold;

wherein the continuous voice is calculated from a voice end node of the user side.

3. The hotel customer service method of claim 1, further comprising, prior to the backup repository for the current hotel:

obtaining characteristic information of all hotels, wherein the characteristic information comprises hotel basic information, hotel service items, hotel room types and hotel evaluation data;

clustering all hotels based on the feature information similarity to obtain one or more associated hotels of which the feature information weighted similarity with the current hotel is greater than a clustering threshold;

and integrating the intelligent knowledge bases of all the related hotels to form a standby knowledge base of the current hotel.

4. The hotel customer service method of claim 3, wherein said searching for answers to questions matching said question questions comprises:

searching whether a question with the matching degree of the question being greater than a matching degree threshold value exists according to the priority sequence of each associated hotel, wherein the matching degree threshold value is smaller than the similarity threshold value;

if yes, pushing the answer of the question to the customer service end every time one question is searched.

5. The hotel customer service method of claim 4, wherein the order of priority is:

arranging the associated hotels according to the characteristic information weighted similarity of the associated hotels and the current hotel from high to low to form the priority order;

the calculation method of the characteristic information weighted similarity Q of the associated hotel and the current hotel comprises the following steps:n is the number of the characteristic information of the associated hotel, s_iIs the similarity, w, of the ith characteristic information of the associated hotel and the corresponding characteristic information of the current hotel_iIs the weight of the ith characteristic information.

6. The hotel customer service method of claim 5, wherein said prior to the prioritization of each associated hotel, further comprising:

detecting whether the question contains keywords corresponding to one or more pieces of characteristic information;

if yes, the weight of the feature information corresponding to the keyword is adjusted upwards, the feature information weighting similarity of each associated hotel and the current hotel is recalculated according to the adjusted weight, and each associated hotel is rearranged; and

and when the question with the matching degree larger than the threshold value of the matching degree exists in the search, searching according to the rearranged priority order.

7. The hotel customer service method of claim 1, further comprising:

updating the intelligent knowledge base of the current hotel every preset period, including:

adding questions and answers which do not exist in the intelligent knowledge base and have the question asking times larger than a first preset value into the intelligent knowledge base; and/or

Removing questions and answers which exist in the intelligent knowledge base and are not asked from the intelligent knowledge base; and/or

And modifying answers of the corresponding questions in the intelligent knowledge base according to the feedback of the customer service end and/or the unsatisfactory evaluation of the user end after receiving the answers.

8. A hotel customer service system based on a knowledge base, comprising:

the call monitoring module is used for monitoring the call state of the customer service end and the question of the user end in real time in the call process of the customer service end and the user end;

the knowledge base searching module is used for searching whether a question with the similarity degree larger than the similarity degree threshold value with the question is existed in the current hotel intelligent knowledge base when the call state meets the triggering condition;

the first pushing module is used for pushing answers of the questions corresponding to the searched maximum similarity to the customer service side when the questions with the similarity larger than the similarity threshold value with the question questions are searched;

and the second pushing module is used for searching answers of the questions matched with the question questions from the standby knowledge base of the current hotel and pushing the answers to the questions to the customer service side when the questions with the similarity degree larger than the similarity degree threshold value with the question questions are not searched.

9. An electronic device, comprising:

a processor;

a memory having executable instructions stored therein;

wherein the executable instructions, when executed by the processor, implement the repository-based hotel customer service method of any of claims 1-7.

10. A computer-readable storage medium storing a program, wherein the program when executed by a processor implements the repository-based hotel customer service method of any of claims 1-7.

Background

The hotel industry is very concerned about user experience, pays attention to quality of service and public praise image, and needs a large number of customer service staff to receive the user's telephone call. However, in terms of the management of knowledge output to customer service, an effective mode is lacked, which mainly includes the following points:

the system has the advantages that a unified knowledge management platform is not available, and customers can remember, write notebook records or excel forms by the traditional brain when receiving the telephone of the user, so that the system is time-consuming, labor-consuming, scattered, not comprehensive, inconvenient to query, time-consuming and labor-consuming;

knowledge understanding of different customer services has deviation, so that the accuracy and the uniformity of the customer service output knowledge cannot be guaranteed, and the user experience and the hotel image are influenced;

at present, some hotels use knowledge bases, but the functions are single, only manual input query of customer service is supported, and quick response in the call process is not facilitated;

the customer service collects a large amount of user data and information through daily work, but the user data and the information cannot be efficiently and sufficiently collected and utilized, and resource waste is caused.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

In view of the above, the invention provides a hotel customer service method, a hotel customer service system, an electronic device and a storage medium based on a knowledge base, which can provide efficient and real-time intelligent knowledge matching output service for hotel customer service through the knowledge base, realize quick response in a call process, ensure effective implementation of the call process, improve customer service efficiency and improve user experience.

One aspect of the present invention provides a hotel customer service method based on a knowledge base, comprising: monitoring the communication state of a customer service end and a question of a user end in real time in the communication process of the customer service end and the user end; when the call state meets a trigger condition, searching whether a question with the similarity degree larger than a similarity degree threshold value to the question exists in an intelligent knowledge base of the current hotel; if yes, pushing the answer of the question corresponding to the searched maximum similarity to the customer service end; if not, searching answers of the questions matched with the question questions from the standby knowledge base of the current hotel, and pushing the answers to the customer service end.

In some embodiments, the trigger condition is: the customer service end inputs a query statement corresponding to the question; or the duration of the voice-off, the pause duration or the repetition frequency of the stop words in the continuous voice of the customer service end exceeds the corresponding threshold value; wherein the continuous voice is calculated from a voice end node of the user side.

In some embodiments, the method further comprises, before the backup knowledge base of the current hotel: obtaining characteristic information of all hotels, wherein the characteristic information comprises hotel basic information, hotel service items, hotel room types and hotel evaluation data; clustering all hotels based on the feature information similarity to obtain one or more associated hotels of which the feature information weighted similarity with the current hotel is greater than a clustering threshold; and integrating the intelligent knowledge bases of all the related hotels to form a standby knowledge base of the current hotel.

In some embodiments, said searching for answers to questions matching said question questions comprises: searching whether a question with the matching degree of the question being greater than a matching degree threshold value exists according to the priority sequence of each associated hotel, wherein the matching degree threshold value is smaller than the similarity threshold value; if yes, pushing the answer of the question to the customer service end every time one question is searched.

In some embodiments, the order of priority is: according to each related hotel and said current hotelArranging each associated hotel from the characteristic information weighted similarity of the previous hotels from high to low to form the priority order; the calculation method of the characteristic information weighted similarity Q of the associated hotel and the current hotel comprises the following steps:n is the number of the characteristic information of the associated hotel, s_iIs the similarity, w, of the ith characteristic information of the associated hotel and the corresponding characteristic information of the current hotel_iIs the weight of the ith characteristic information.

In some embodiments, before the prioritizing of the associated hotels, the method further comprises: detecting whether the question contains keywords corresponding to one or more pieces of characteristic information; if yes, the weight of the feature information corresponding to the keyword is adjusted upwards, the feature information weighting similarity of each associated hotel and the current hotel is recalculated according to the adjusted weight, and each associated hotel is rearranged; and when the question with the matching degree larger than the threshold value of the matching degree exists in the search, searching according to the rearranged priority order.

In some embodiments, the hotel customer service method further comprises: updating the intelligent knowledge base of the current hotel every preset period, including: adding questions and answers which do not exist in the intelligent knowledge base and have the question asking times larger than a first preset value into the intelligent knowledge base; and/or removing questions and answers which exist in the intelligent knowledge base and are not asked from the intelligent knowledge base; and/or modifying the answer of the corresponding question in the intelligent knowledge base according to the feedback of the customer service end and/or the dissatisfaction evaluation of the user end after receiving the answer.

Another aspect of the present invention provides a hotel customer service system based on a knowledge base, comprising: the call monitoring module is used for monitoring the call state of the customer service end and the question of the user end in real time in the call process of the customer service end and the user end; the knowledge base searching module is used for searching whether a question with the similarity degree larger than the similarity degree threshold value with the question is existed in the current hotel intelligent knowledge base when the call state meets the triggering condition; the first pushing module is used for pushing answers of the questions corresponding to the searched maximum similarity to the customer service side when the questions with the similarity larger than the similarity threshold value with the question questions are searched; and the second pushing module is used for searching answers of the questions matched with the question questions from the standby knowledge base of the current hotel and pushing the answers to the questions to the customer service side when the questions with the similarity degree larger than the similarity degree threshold value with the question questions are not searched.

Yet another aspect of the present invention provides an electronic device, comprising: a processor; a memory having executable instructions stored therein; wherein the executable instructions, when executed by the processor, implement the repository-based hotel customer service method of any of the above embodiments.

Yet another aspect of the present invention provides a computer-readable storage medium storing a program which, when executed by a processor, implements the repository-based hotel customer service method of any of the above embodiments.

Compared with the prior art, the invention has the beneficial effects that:

a complete knowledge management mechanism is formed through a knowledge base, high-efficiency real-time intelligent knowledge matching output service is provided for hotel customer service, and effective management of the customer service is realized; by monitoring the call state of the customer service end and the question asked at the user end in real time, the intelligent knowledge base is searched immediately when the call state meets the trigger condition, so that the quick response of the call process is realized; when the intelligent knowledge base is searched, the standby knowledge base is further searched, so that the effective operation of the call process is ensured, the customer service efficiency is improved, and the user experience is improved;

furthermore, the hotel knowledge base can be updated through a periodic feedback mechanism to form a complete knowledge flow closed loop, the integrity and the matching degree of the knowledge base are improved, the service use viscosity is increased, and the effective management of the service and the service efficiency are further improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

Figure 1 shows a schematic diagram of the steps of a knowledge base based hotel customer service method in an embodiment of the invention;

FIG. 2 is a schematic diagram illustrating the steps of forming a standby knowledge base of a current hotel in an embodiment of the present invention;

FIG. 3 is a diagram illustrating a scenario of adjusting the search order of the backup repository in an embodiment of the present invention;

figure 4 shows a schematic block diagram of a knowledge base based hotel customer service system in an embodiment of the present invention;

FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the invention;

fig. 6 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

The drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

In addition, the flow shown in the drawings is only an exemplary illustration, and not necessarily includes all the steps. For example, some steps may be divided, some steps may be combined or partially combined, and the actual execution sequence may be changed according to the actual situation. The use of "first," "second," and similar terms in the detailed description is not intended to imply any order, quantity, or importance, but rather is used to distinguish one element from another. It should be noted that features of the embodiments of the invention and of the different embodiments may be combined with each other without conflict.

Fig. 1 shows the main steps of the hotel customer service method based on the knowledge base in an embodiment, and referring to fig. 1, the hotel customer service method based on the knowledge base comprises: step S110, monitoring the communication state of the customer service end and the question of the user end in real time in the communication process of the customer service end and the user end; step S120, when the call state meets the triggering condition, searching whether a question with the similarity degree larger than the similarity degree threshold value with the question exists in the current hotel intelligent knowledge base; if yes, step S130 is executed, the answer to the question corresponding to the searched maximum similarity is pushed to the customer service end; if not, step S140 is executed, the answer of the question matched with the question is searched from the standby knowledge base of the current hotel, and the answer is pushed to the customer service end.

Through the knowledge base, a complete knowledge management mechanism can be formed, high-efficiency real-time intelligent knowledge matching output service is provided for hotel customer service, and effective management of the customer service is realized; by monitoring the call state of the customer service end and the question asked at the user end in real time, the intelligent knowledge base is searched immediately when the call state meets the trigger condition, so that the quick response of the call process is realized; when the intelligent knowledge base is searched, the standby knowledge base is further searched, so that the effective proceeding of the call process is ensured, the customer service efficiency is improved, and the user experience is improved.

The real-time monitoring of the call state of the customer service end and the question asking of the user end can be realized by the existing voice monitoring service. In one embodiment, the meeting of the trigger condition in the call state specifically refers to any one of the following two cases: the customer service end inputs the query sentence corresponding to the question, namely the customer service end can manually query the question related to the question of the user according to the requirement in the process of communicating with the user. The intelligent knowledge base can quickly and accurately inquire the corresponding question and answer by using the intelligent inquiry function only by inputting the key words of the question by the customer service end, and pushes the key words and the answer to the customer service end, so that the customer service can provide accurate and complete answers for the user according to the answer, and the efficiency is improved.

Or when the voice-off duration, the pause duration or the repeated frequency of the stop words in the continuous voice of the customer service end exceeds the corresponding threshold, judging that the call state meets the triggering condition, and automatically inquiring the relevant questions and answers. Wherein, the continuous voice is calculated from the voice end node of the user terminal. Specifically, in one example, the user end issues a question: when the last decoration of the hotels is performed, the continuous voice state of the customer service end is monitored from the voice end node of the user end; if the duration of the voice-off of the customer service end exceeds a corresponding threshold (for example, the voice is continuously emitted for more than 2 seconds), or the pause duration exceeds a corresponding threshold (for example, the voice of the customer service end is not emitted for 2 seconds continuously from a voice end node of the customer service end), or the repetition frequency of the stop words exceeds a corresponding threshold (for example, the voice content continuously emitted by the customer service end for 2 seconds only contains the stop words of the words, the words are the words, the words and the like, and the stop words can be set in advance), it is determined that the customer service end cannot accurately answer the question of the customer end depending on the self-ability, so that the intelligent knowledge base is searched immediately automatically, the manual input of the time of the customer service end is not needed, and the quick response of the call process is realized.

The intelligent knowledge base can comprise a question-answer base and a document base, and a plurality of groups of question-answer pairs are stored. When searching the intelligent knowledge base, firstly extracting a question keyword from a question of a user end, then traversing and searching the intelligent knowledge base by using the question keyword, and finding an index of a similar question with the similarity of the question keyword being greater than a similarity threshold value. If the intelligent knowledge base has the similar question to the question asked at the user side, pushing the answer of the question corresponding to the searched maximum similarity to the customer service side; and if the intelligent knowledge base does not have the problem similar to the question of the user side, skipping to the standby knowledge base of the current hotel.

Fig. 2 shows the main steps of forming the standby knowledge base of the current hotel in an embodiment, and referring to fig. 2, when the intelligent knowledge base of each hotel is established, the hotel customer service method further includes: step S210, obtaining characteristic information of all hotels, wherein the characteristic information comprises hotel basic information, hotel service items, hotel room types and hotel evaluation data; step S220, clustering all hotels based on the feature information similarity, and obtaining one or more associated hotels of which the feature information weighted similarity with the current hotel is greater than a clustering threshold; and step S230, integrating the intelligent knowledge bases of all the related hotels to form a standby knowledge base of the current hotel.

The hotel basic information comprises information such as hotel names, hotel addresses and hotel telephones, the hotel service items comprise pick-up and delivery machine services, guest room services, catering services and entertainment services, and the hotel evaluation data can be obtained within a period of time. And respectively calculating the characteristic information weighted similarity of each hotel and the current hotel when clustering all the hotels based on the characteristic information similarity, and clustering one or more associated hotels with the characteristic information weighted similarity greater than a clustering threshold value with the current hotel.

A calculation mode of the characteristic information weighting similarity Q of the associated hotel and the current hotel is as follows: n is the number of the characteristic information of the associated hotel, s_iIs the similarity between the ith characteristic information of the associated hotel and the corresponding characteristic information of the current hotel, w_iIs the weight of the ith characteristic information. Similarity of characteristic informationThe degree calculation can adopt semantic similarity calculation and other modes, and the description is not expanded.

And after the related hotels of the current hotel are obtained, the question-answer pairs in the intelligent knowledge bases of all the related hotels are combined together to form a standby knowledge base of the current hotel.

In one embodiment, searching the self-contained knowledge base for answers to questions matching the question questions comprises: searching whether a question with a matching degree larger than a matching degree threshold value with the question exists according to the priority sequence of each associated hotel, wherein the matching degree threshold value is smaller than a similarity threshold value; if yes, the answer of the question is pushed to the customer service end every time one question is searched, and the customer service end can be ensured to timely acquire the answer of the relevant question. Wherein, the priority order of each associated hotel is as follows: and arranging the associated hotels according to the characteristic information weighted similarity of the associated hotels and the current hotel from high to low to form a priority order.

Further, before searching the standby database according to the priority order of each associated hotel, the method also comprises the step of adjusting the search order of the standby database according to the question of the user side. Fig. 3 illustrates a scenario of adjusting the search order of the backup repository in an embodiment, and in conjunction with fig. 3, the priority order of each associated hotel in the backup repository 300 is initially: associated Hotel A (its characteristic information weighted similarity Q with the current hotel)_A95%) → associate hotel B (its characteristic information weighted similarity Q to the current hotel Q)_B93%) → associate hotel C (its characteristic information weighted similarity Q to the current hotel Q)_C92%). Adjusting the search order of the alternate knowledge base 300 includes: detecting whether the question includes a keyword corresponding to one or more feature information (in this embodiment, if the question is "can be sent", for example, it is detected that the question includes a keyword "send" corresponding to a hotel service item); if so, the weight of the feature information corresponding to the keyword is adjusted up (in this embodiment, the weight corresponding to the service item of the wine shop is adjusted up, the up-adjustment proportion can be determined according to the number of specific items hit in the service item of the wine shop, and in this embodiment, only the receiving and sending machine is hit, so the up-adjustment proportion is 10%) Recalculating the characteristic information weighted similarity of each associated hotel and the current hotel according to the adjusted weight, and rearranging each associated hotel; for example, after the feature information weighted similarity between each associated hotel and the current hotel is recalculated according to the adjusted weight, the feature information weighted similarities corresponding to the associated hotel a, the associated hotel B, and the associated hotel C are respectively: q_A＝96％，Q_B＝98％，Q_CAnd 93%, forming an adjusted standby knowledge base 300', wherein the rearranged priority order of each associated hotel is as follows: associated hotel B → associated hotel a → associated hotel C.

When searching whether a question with the matching degree larger than the matching degree threshold value exists or not, searching is carried out according to the rearranged priority order, so that the question and the answer matched with the question at the user side are searched most quickly, the customer service efficiency is improved, and the user satisfaction is improved.

Further, in one embodiment, the hotel customer service method further comprises: updating the intelligent knowledge base of the current hotel every preset period (for example, one week), including: adding questions and answers which do not exist in the intelligent knowledge base and are asked for times greater than a first preset value (for example, 5 times) to the intelligent knowledge base; and/or removing questions and answers which exist in the intelligent knowledge base and are not asked from the intelligent knowledge base; and/or modifying the answers of the corresponding questions in the intelligent knowledge base according to the feedback of the customer service end and/or the unsatisfactory evaluation of the user end after receiving the answers.

The feedback of the customer service end specifically means that the customer service can feed back the search result of the problem, record the unknown problem, the unsatisfied problem and the like, and then the administrator supplements, adjusts and modifies the unknown problem, and meanwhile, the customer service can also carry out deep learning through artificial intelligence to supplement the integrity and the matching degree of knowledge. The deep learning based on artificial intelligence can adopt the existing technology and is not explained. The administrator can add, delete, check and change the questions and answers and the documents, enable the forbidden operation, sort and sort, set the authority and the like, and the unified and standardized intelligent knowledge base is facilitated. Through the authority system, different access authorities can be given to an administrator and a customer service, and the safety and the reliability of the intelligent knowledge base are ensured.

The hotel knowledge base is updated by setting questions and answers and documents by an administrator, inquiring and using the customer service and feeding back results, recording unknown problems and unsatisfied problems, artificially intelligently analyzing and modifying and supplementing the cyclic process by the administrator and utilizing a periodic feedback mechanism, so that a complete knowledge flow closed loop is formed, the integrity and the matching degree of the knowledge base are improved, the use viscosity of the customer service is increased, and the effective management of the customer service and the customer service efficiency are further improved.

The embodiment of the invention also provides a hotel customer service system based on the knowledge base, which can be used for realizing the hotel customer service method based on the knowledge base described in any embodiment. The features and principles of the hotel customer service method described in any of the above embodiments can be applied to the following hotel customer service system embodiments. In the following embodiments of the hotel customer service system, the features and principles already elucidated with respect to the knowledge-base based hotel customer service are not repeated.

Figure 4 illustrates the major modules of the repository-based hotel services system in one embodiment, and referring to figure 4, the repository-based hotel services system 400 includes: the call monitoring module 410 is used for monitoring the call state of the customer service end and the question asked by the user end in real time in the call process of the customer service end and the user end; the knowledge base searching module 420 is configured to search whether a question with a similarity greater than a similarity threshold to the question exists in the current hotel intelligent knowledge base when the call state meets the trigger condition; the first pushing module 430 is configured to, when a question with similarity to the question being greater than a similarity threshold is searched, push the answer to the question corresponding to the searched maximum similarity to the customer service end; and the second pushing module 440 is configured to, when a question with similarity to the question being greater than the similarity threshold is not searched, search for an answer to the question matching the question from the standby knowledge base of the current hotel, and push the answer to the customer service end.

Further, the hotel customer service system 400 based on the knowledge base may further include modules for implementing other process steps of the above embodiments of the hotel customer service method, and specific principles of each module may refer to the description of the above embodiments of the hotel customer service method, and will not be described again here.

As described above, the hotel customer service system based on the knowledge base can establish a complete knowledge management mechanism through the knowledge base, provide efficient and real-time intelligent knowledge matching output service for hotel customer service, and realize effective management of the customer service; by monitoring the call state of the customer service end and the question asked at the user end in real time, the intelligent knowledge base is searched immediately when the call state meets the trigger condition, so that the quick response of the call process is realized; when the intelligent knowledge base is searched, the standby knowledge base is further searched, so that the effective operation of the call process is ensured, the customer service efficiency is improved, and the user experience is improved; furthermore, the hotel knowledge base can be updated through a periodic feedback mechanism to form a complete knowledge flow closed loop, the integrity and the matching degree of the knowledge base are improved, the service use viscosity is increased, and the effective management of the service and the service efficiency are further improved.

The embodiment of the invention also provides electronic equipment, which comprises a processor and a memory, wherein the memory stores executable instructions, and the executable instructions are executed by the processor to realize the hotel customer service method based on the knowledge base, which is described in any embodiment.

As described above, the electronic equipment can establish a complete knowledge management mechanism through the knowledge base, provide high-efficiency real-time intelligent knowledge matching output service for hotel customer service, and realize effective management of the customer service; by monitoring the call state of the customer service end and the question asked at the user end in real time, the intelligent knowledge base is searched immediately when the call state meets the trigger condition, so that the quick response of the call process is realized; when the intelligent knowledge base is searched, the standby knowledge base is further searched, so that the effective operation of the call process is ensured, the customer service efficiency is improved, and the user experience is improved; furthermore, the hotel knowledge base can be updated through a periodic feedback mechanism to form a complete knowledge flow closed loop, the integrity and the matching degree of the knowledge base are improved, the service use viscosity is increased, and the effective management of the service and the service efficiency are further improved.

Fig. 5 is a schematic structural diagram of an electronic device in an embodiment of the present invention, and it should be understood that fig. 5 only schematically illustrates various modules, and these modules may be virtual software modules or actual hardware modules, and the combination, the splitting, and the addition of the remaining modules of these modules are within the scope of the present invention.

As shown in fig. 5, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.

Wherein the storage unit stores a program code, which is executable by the processing unit 610, to cause the processing unit 610 to perform the steps of the repository based hotel customer service method described in any of the embodiments above. For example, processing unit 610 may perform the steps shown in fig. 1.

The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include programs/utilities 6204 including one or more program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 600 may also communicate with one or more external devices 700, and the external devices 700 may be one or more of a keyboard, a pointing device, a bluetooth device, and the like. The external devices 700 enable a user to interactively communicate with the electronic device 600. The electronic device 600 may also be capable of communicating with one or more other computing devices, including routers, modems. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.

The embodiment of the present invention further provides a computer-readable storage medium for storing a program, and when the program is executed, the method for hotel customer service based on a knowledge base described in any of the above embodiments is implemented. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the repository-based hotel customer service method described in any of the embodiments above, when the program product is run on the terminal device.

As described above, the computer-readable storage medium of the invention can establish a complete knowledge management mechanism through the knowledge base, provide high-efficiency real-time intelligent knowledge matching output service for hotel customer service, and realize effective management of the customer service; by monitoring the call state of the customer service end and the question asked at the user end in real time, the intelligent knowledge base is searched immediately when the call state meets the trigger condition, so that the quick response of the call process is realized; when the intelligent knowledge base is searched, the standby knowledge base is further searched, so that the effective operation of the call process is ensured, the customer service efficiency is improved, and the user experience is improved; furthermore, the hotel knowledge base can be updated through a periodic feedback mechanism to form a complete knowledge flow closed loop, the integrity and the matching degree of the knowledge base are improved, the service use viscosity is increased, and the effective management of the service and the service efficiency are further improved.

Fig. 6 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 6, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of readable storage media include, but are not limited to: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device, such as through the internet using an internet service provider.

The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.