Method, device and equipment for identifying service attitude of hotel service personnel and storage medium

Abstract

The invention is suitable for the technical field of voice analysis, and provides a hotel service personnel service attitude identification method and device, equipment and a storage medium. The method comprises the steps of obtaining service voice between a service staff and a customer and a corresponding voice scene type, inputting the voice scene type and the service voice into a trained target model, obtaining a service attitude score of the service staff output by the target model, and determining the service attitude of the service staff according to the service attitude score, the target model comprises a plurality of modules, different modules correspond to different voice scene types, and different modules are obtained through training based on a plurality of historical service voices under the corresponding voice scene types and corresponding historical service attitude scores. According to the method and the device, the service attitude of each service staff can be comprehensively and accurately determined, so that the service staff can be effectively managed subsequently based on the service attitude of each service staff, and the service quality and the customer satisfaction are improved.

Description

Technical Field

[0001] The present application relates to the field of speech analysis technology, and in particular to a method, device, equipment and storage medium for identifying the service attitude of hotel service personnel. Background Art

[0002] At present, the service quality of the hotel industry has become the key to influencing tourists' satisfaction. Among them, the service behavior of hotel service staff, especially the service attitude, is closely related to customer satisfaction. Therefore, accurately determining the service attitude of service staff and managing service staff based on this is very important for improving service quality and customer satisfaction.

[0003] In the related art, the service attitude of service personnel is usually identified and judged by manually spot-checking the service voice between service personnel and customers. However, the proportion of manual spot-checking is low, and it is impossible to comprehensively identify and check the service attitude of service personnel, and thus it is impossible to effectively manage service personnel, which affects service quality and customer satisfaction. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for identifying the service attitude of hotel service personnel, so as to accurately and comprehensively identify the service attitude of service personnel, thereby effectively managing the service personnel subsequently and improving service quality and customer satisfaction.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying the service attitude of hotel service personnel, comprising:

[0006] Acquire the service speech between the hotel service staff and the customer when the hotel service staff provides service to the customer, as well as the corresponding speech scene type;

[0007] Input the speech scene type and the service speech into a trained target model, and obtain a service attitude score of the service personnel output by the target model; wherein the target model includes multiple modules, different modules correspond to different speech scene types, and different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under corresponding speech scene types;

[0008] The service attitude of the service personnel is determined according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

[0009] In a possible implementation, before inputting the speech scene type and the service speech into a trained target model to obtain a service attitude score of the service personnel output by the target model, the method further includes:

[0010] Obtain multiple historical service voices and historical service attitude scores corresponding to different service personnel, as well as the voice scene type corresponding to each historical service voice;

[0011] By using historical service voices under different voice scene types and corresponding historical service attitude scores, each module of the target model is trained respectively to obtain a trained target model.

[0012] In a possible implementation, the historical service voices under different voice scene types and the corresponding historical service attitude scores are used to train the modules of the target model respectively to obtain the trained target model, including:

[0013] For each type of speech scene type, input the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the predicted score output by the module; according to the predicted score and the historical service attitude score corresponding to the historical service speech, adjust the module corresponding to the type of speech scene type in the target model;

[0014] Based on the adjusted modules, a trained target model is obtained.

[0015] In a possible implementation, for each type of speech scene type, adjusting the module corresponding to the type of speech scene type in the target model according to the predicted score and the historical service attitude score corresponding to the historical service speech includes:

[0016] Determining an error value based on a difference between the predicted score and a historical service attitude score corresponding to the historical service speech;

[0017] Determine whether the error value is greater than a preset threshold;

[0018] If the error value is greater than the preset threshold, the module corresponding to the type of speech scene type in the target model is adjusted, and based on the module corresponding to the type of speech scene type in the adjusted target model, the step of inputting the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the prediction score output by the module is re-executed until the error value is less than or equal to the preset threshold.

[0019] In a possible implementation, obtaining the voice scene type includes:

[0020] Acquire the location information of the service personnel when the service personnel is providing service to the customer; the location information includes the WiFi information of the WiFi device to which the recording device carried by the service personnel is connected, and the recording device is used to record the service voice;

[0021] Determine a corresponding WiFi device according to the WiFi information;

[0022] The voice scene type is determined based on an installation location of the WiFi device.

[0023] In a possible implementation, obtaining the voice scene type includes:

[0024] Inputting the service speech into a trained scene recognition model to obtain the speech scene type output by the scene recognition model;

[0025] The scene recognition model is obtained based on a plurality of historical service voice trainings under different voice scene types.

[0026] In a possible implementation, determining the service attitude of the service personnel according to the service attitude score includes:

[0027] If the service attitude score is the first score, the service attitude of the service personnel is determined to be the first attitude; if the service attitude score is the second score, the service attitude of the service personnel is determined to be the second attitude; if the service attitude score is the third score, the service attitude of the service personnel is determined to be the third attitude; if the service attitude score is the fourth score, the service attitude of the service personnel is determined to be the fourth attitude; if the service attitude score is the fifth score, the service attitude of the service personnel is determined to be the fifth attitude;

[0028] The first score, the second score, the third score, the fourth score and the fifth score decrease in sequence, and the first attitude, the second attitude, the third attitude, the fourth attitude and the fifth attitude become worse in sequence.

[0029] In a second aspect, an embodiment of the present application provides a device for identifying the service attitude of hotel service personnel, comprising:

[0030] The acquisition module is used to acquire the service speech between the hotel service staff and the customer when the hotel service staff provides service to the customer, as well as the corresponding speech scene type.

[0031] A module is obtained, which is used to input the voice scene type and the service voice into a trained target model to obtain a service attitude score of the service personnel output by the target model; wherein the target model includes multiple modules, different modules correspond to different voice scene types, and different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under the corresponding voice scene types.

[0032] A determination module is used to determine the service attitude of the service personnel according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method for identifying the service attitude of hotel service personnel as described in any one of the first aspects is implemented.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying the service attitude of hotel service personnel as described in any one of the first aspects is implemented.

[0035] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0036] The hotel service staff service attitude recognition method, device, equipment and storage medium provided in the embodiment of the present application obtain the service speech between the service staff and the customer and the corresponding voice scene type, and based on the above voice scene type, use the trained target model to process the service speech to obtain the service attitude score of the service staff, and then determine the service attitude of the service staff according to the service attitude score, wherein the target model includes different modules corresponding to different voice scene types, and the different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under the corresponding voice scene types to improve the accuracy and reliability of the target model. The present application can comprehensively and accurately determine the service attitude of each service staff, so that the service staff can be effectively managed based on the service attitude of each service staff in the future, and the service quality and customer satisfaction can be improved.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0040] Figure 2 It is a flowchart of a method for identifying the service attitude of hotel service personnel provided in an embodiment of the present application;

[0041] Figure 3 It is a structural schematic diagram of a device for identifying the service attitude of hotel service personnel provided by an embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0043] The present application is described more clearly below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the effects of the present application, but are not intended to limit the present application in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements may be made without departing from the concept of the present application. These all fall within the scope of protection of the present application.

[0044] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0045] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0046] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0047] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0048] In addition, the “plurality” mentioned in the embodiments of the present application should be interpreted as two or more.

[0049] With the idea of ​​being able to comprehensively identify and check the service attitude of service personnel, the service voice between service personnel and customers and the corresponding voice scene types can be obtained, and based on the above voice scene types, the service voice can be processed using the trained target model to obtain the service attitude score of the service personnel, and then the service attitude of the service personnel can be determined based on the service attitude score. Subsequently, the service personnel can be effectively managed based on their service attitude to improve service quality and customer satisfaction.

[0050] First reference Figure 1 , Figure 1 A schematic diagram of an application scenario provided according to an embodiment of the present application is schematically shown, and the devices involved in the application scenario include electronic devices.

[0051] A trained target model is deployed on the above-mentioned electronic device. The electronic device inputs the service voice between the service personnel and the customer and the corresponding voice scene type into the above-mentioned target model to obtain a service attitude score for the service personnel, and then determines the service attitude of the service personnel based on the service attitude score.

[0052] Optionally, the devices involved in the application scenario also include a recording device, and the electronic device and the recording device can communicate with each other through a network. The recording device is carried by each service personnel to record service voice.

[0053] Combine the following Figure 1 For application scenarios, refer to Figure 2 To describe the hotel service staff service attitude identification method provided according to the exemplary embodiment of the present application.

[0054] Figure 2 1 is a flow chart of a method for identifying the service attitude of hotel service personnel provided in an embodiment of the present application. Figure 2 As shown, the method in the embodiment of the present application may include:

[0055] Step 201: Acquire the service speech between the hotel service staff and the customer when the hotel service staff is serving the customer, and the corresponding speech scene type.

[0056] For example, hotel service personnel may wear recording devices or radio equipment to record the conversation between the service personnel and the customer when the service personnel provide service to the customer, that is, to record the service voice.

[0057] It should be noted that, in order to protect customer privacy, service personnel who work only in public places of the hotel wear recording devices or radios, which have privacy recognition functions to ensure that the service voices obtained do not involve customer privacy. For example, when the recording device recognizes words such as "ID card", "telephone" and "address", it stops recording to protect customer privacy.

[0058] The voice scene type corresponding to the service voice refers to the type of place where the service voice occurs, such as the hotel lobby, restaurant, lobby bar and executive lounge. For example, the service voice in the lobby can include registration consultation, the service voice in the restaurant can include ordering communication, and the service voice in the lobby bar and executive lounge can include ordering communication, etc.

[0059] In some embodiments, when obtaining the voice scene type, the location information of the service personnel when the service personnel is providing service to the customer can be obtained, wherein the location information includes the WiFi information of the WiFi device to which the recording device carried by the service personnel is connected. Thereafter, the corresponding WiFi device is determined based on the WiFi information, and the voice scene type is determined based on the installation location of the WiFi device.

[0060] Exemplarily, the recording device carried by the service personnel can be connected to the network, such as by connecting to a WiFi device, so that the recording device can obtain the WiFi information of the connected WiFi device, such as the WiFi name or address. This embodiment obtains the WiFi information of the WiFi device to which the recording device carried by the service personnel is connected when the service personnel provides service to the customer, as the current location information of the service personnel, and then determines the corresponding WiFi device according to the above WiFi information, and determines the voice scene type based on the installation location of the WiFi device. If it is determined that the WiFi device is installed in the lobby, the voice scene type is determined to be the lobby. Thus, the voice scene type corresponding to the service voice obtained when the service personnel and the customer have a conversation can be obtained.

[0061] In some embodiments, when obtaining the voice scene type, the service voice can also be input into a trained scene recognition model to obtain the voice scene type output by the scene recognition model, wherein the scene recognition model is trained based on multiple historical service voices under different voice scene types.

[0062] Exemplarily, before obtaining the voice scene type, the scene recognition model can be trained. Specifically, multiple historical service voices under different voice scene types are obtained, the historical service voices are input into the voice recognition model, the predicted scene type output by the voice recognition model is obtained, and the scene recognition model is adjusted based on the difference between the predicted scene type and the voice scene type corresponding to the historical service voice, and the above steps of inputting the historical service voice into the voice recognition model, obtaining the predicted scene type output by the voice recognition model, and adjusting the scene recognition model based on the difference between the predicted scene type and the voice scene type corresponding to the historical service voice are repeated until the preset number of times is reached to obtain a trained scene recognition model.

[0063] Optionally, the scene model recognition can be the above-mentioned target model. In this case, the target model can be a multimodal learning model, whose input is the service speech and whose output is the corresponding speech scene type and the service attitude score of the service personnel.

[0064] Step 202: Input the speech scene type and the service speech into the trained target model to obtain the service attitude score of the service personnel output by the target model; wherein the target model includes multiple modules, different modules correspond to different speech scene types, and different modules are trained based on multiple historical service voices under the corresponding speech scene types and the corresponding historical service attitude scores.

[0065] Exemplarily, after the present embodiment inputs the speech scene type and the service speech into the trained target model, the target model processes the service speech based on the speech scene type using the module therein corresponding to the speech scene type, and outputs a service attitude score for the service personnel.

[0066] In one possible implementation, before the speech scene type and the service speech are input into the trained target model, the target model can also be trained. Specifically, multiple historical service speech and historical service attitude scores corresponding to different service personnel, as well as the speech scene type corresponding to each historical service speech, can be obtained. Then, the historical service speech under different speech scene types and the corresponding historical service attitude scores are used to train each module of the target model to obtain a trained target model.

[0067] Optionally, this embodiment collects customer feedback such as customer evaluations corresponding to each historical service voice, and preprocesses the customer evaluations, including removing duplicate comments, cleaning irrelevant information, and performing Chinese word segmentation. Afterwards, the hotel staff can use a 5-level Likert scale to quantify the customer evaluations as the historical service attitude scores corresponding to the historical service voices.

[0068] The standard for quantitative scoring of customer reviews can be: 5 points for positive reviews, in which customers highly evaluate the hotel's services, facilities, environment, etc.; 4 points for relatively positive reviews, in which customers give high evaluations to the hotel's services, facilities, environment, etc., but contain some minor deficiencies or suggestions for improvement; 3 points for neutral reviews, in which customers mention both advantages and disadvantages, and the overall evaluation is average; 2 points for relatively negative reviews, in which customers express a lot of dissatisfaction with the hotel's services, facilities, environment, etc.; 1 point for very negative reviews, in which customers express serious dissatisfaction or complaints about the hotel.

[0069] In some embodiments, when a trained target model is obtained, for each type of speech scene type, the historical service speech under that type of speech scene type is input into the module corresponding to that type of speech scene type in the target model to obtain the predicted score output by the module. Thereafter, based on the predicted score and the historical service attitude score corresponding to the historical service speech, the module corresponding to that type of speech scene type in the target model is adjusted, and based on the adjusted modules, a trained target model is obtained.

[0070] In this embodiment, for each type of voice scene type, multiple historical service voices under this type of voice scene type can be input into the module corresponding to this type of voice scene type in the target model to obtain multiple corresponding prediction scores, and based on the multiple prediction scores and the corresponding multiple historical service attitude scores, the module corresponding to this type of voice scene type in the target model can be adjusted.

[0071] Exemplarily, when adjusting the module corresponding to this type of speech scene type in the target model, the error value can be determined based on the difference between the predicted score and the historical service attitude score corresponding to the historical service speech, and it can be judged whether the error value is greater than a preset threshold. If the error value is greater than the preset threshold, the module corresponding to this type of speech scene type in the target model is adjusted, and based on the module corresponding to this type of speech scene type in the adjusted target model, the step of inputting the historical service speech under this type of speech scene type into the module corresponding to this type of speech scene type in the target model is re-executed to obtain the predicted score output by the module until the error value is less than or equal to the preset threshold.

[0072] For example, in this embodiment, the error value may be obtained according to the ratio between the number of predicted scores whose values ​​are equal to the corresponding historical service attitude scores among the multiple predicted scores and the number of the multiple predicted scores.

[0073] Here, after training each module in the target model and obtaining a trained target model based on the adjusted modules, cross-validation or test set validation can be performed. When the cross-validation or test set validation fails, the target model can be re-trained to ensure the accuracy and reliability of the final target model.

[0074] It should be noted that all voice, text or other format data acquired in this embodiment are encrypted when stored to ensure data security.

[0075] Here, since the key words in the service speech occurring in different voice scene types are different, in this embodiment, the historical service speech and the corresponding historical service attitude scores under each voice scene type are used to train each module included in the target model respectively. This allows each module in the target model to better recognize and score the service speech under the corresponding voice scene type, thereby improving the accuracy of each module and thus improving the accuracy of the target model.

[0076] Exemplarily, each module in the target model may share some parameters that reflect common features, while retaining some parameters that reflect specific features. Each module in the target model may also be an independent sub-model.

[0077] In this way, by inputting the service voices of different service personnel and the corresponding voice scene types into the trained target model, the service attitude scores of different service personnel can be obtained.

[0078] Step 203: Determine the service attitude of the service personnel according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

[0079] For example, if the service attitude score is the first score, the service attitude of the service personnel is determined to be the first attitude, if the service attitude score is the second score, the service attitude of the service personnel is determined to be the second attitude, if the service attitude score is the third score, the service attitude of the service personnel is determined to be the third attitude, if the service attitude score is the fourth score, the service attitude of the service personnel is determined to be the fourth attitude, and if the service attitude score is the fifth score, the service attitude of the service personnel is determined to be the fifth attitude. The first score, the second score, the third score, the fourth score and the fifth score decrease in sequence, and the first attitude, the second attitude, the third attitude, the fourth attitude and the fifth attitude become worse in sequence.

[0080] As can be seen from the above, a 5-level Likert scale can be used to quantify customer evaluations. In this embodiment, the first score, the second score, the third score, the fourth score and the fifth score can be 5 points, 4 points, 3 points, 2 points and 1 point respectively. Correspondingly, the first attitude, the second attitude, the third attitude, the fourth attitude and the fifth attitude are very good, good, average, poor and very poor respectively.

[0081] In this way, according to the service attitude scores of different service personnel, the service attitudes of different service personnel can be obtained, that is, the service attitudes of each service personnel can be obtained comprehensively and accurately, so that the service personnel can be effectively managed based on the service attitudes of each service personnel in the future, such as conducting relevant service training, formulating relevant policies, etc., so as to improve service quality and customer satisfaction, etc.

[0082] The method for identifying the service attitude of hotel service personnel provided in the embodiment of the present application obtains the service speech between the service personnel and the customer and the corresponding voice scene type, and based on the above voice scene type, uses the trained target model to process the service speech, obtains the service attitude score of the service personnel, and then determines the service attitude of the service personnel according to the service attitude score, wherein the target model includes different modules corresponding to different voice scene types, and the different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under the corresponding voice scene types to improve the accuracy and reliability of the target model. The present application can comprehensively and accurately determine the service attitude of each service personnel, so that the service personnel can be effectively managed based on the service attitude of each service personnel in the future, and the service quality and customer satisfaction can be improved.

[0083] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] Figure 3 Schematic diagram of the structure of a device for identifying the service attitude of hotel service personnel provided by an embodiment of the present application. Figure 3 As shown, the device for identifying the service attitude of hotel service personnel provided in this embodiment may include: an acquisition module 301 , an obtaining module 302 and a determination module 303 .

[0085] The acquisition module 301 is used to acquire the service voice between the hotel service personnel and the customer when the hotel service personnel provides service to the customer, as well as the corresponding voice scene type.

[0086] Obtain module 302, which is used to input the voice scene type and the service voice into a trained target model to obtain a service attitude score of the service personnel output by the target model; wherein the target model includes multiple modules, different modules correspond to different voice scene types, and different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under the corresponding voice scene types.

[0087] The determination module 303 is used to determine the service attitude of the service personnel according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

[0088] In a possible implementation, the obtaining module 302 is further used for:

[0089] Obtain multiple historical service voices and historical service attitude scores corresponding to different service personnel, as well as the voice scene type corresponding to each historical service voice;

[0090] By using historical service voices under different voice scene types and corresponding historical service attitude scores, each module of the target model is trained respectively to obtain a trained target model.

[0091] In a possible implementation, the obtaining module 302 is further used for:

[0092] For each type of speech scene type, input the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the predicted score output by the module; according to the predicted score and the historical service attitude score corresponding to the historical service speech, adjust the module corresponding to the type of speech scene type in the target model;

[0093] Based on the adjusted modules, a trained target model is obtained.

[0094] In a possible implementation, the obtaining module 302 is further used for:

[0095] Determining an error value based on a difference between the predicted score and a historical service attitude score corresponding to the historical service speech;

[0096] Determine whether the error value is greater than a preset threshold;

[0097] If the error value is greater than the preset threshold, the module corresponding to the type of speech scene type in the target model is adjusted, and based on the module corresponding to the type of speech scene type in the adjusted target model, the step of inputting the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the prediction score output by the module is re-executed until the error value is less than or equal to the preset threshold.

[0098] In a possible implementation, the acquisition module 301 is further configured to:

[0099] Acquire the location information of the service personnel when the service personnel is providing service to the customer; the location information includes the WiFi information of the WiFi device to which the recording device carried by the service personnel is connected, and the recording device is used to record the service voice;

[0100] Determine a corresponding WiFi device according to the WiFi information;

[0101] The voice scene type is determined based on an installation location of the WiFi device.

[0102] In a possible implementation, the acquisition module 301 is further configured to:

[0103] Inputting the service speech into a trained scene recognition model to obtain the speech scene type output by the scene recognition model;

[0104] The scene recognition model is obtained based on a plurality of historical service voice trainings under different voice scene types.

[0105] In a possible implementation, the determining module 303 is further configured to:

[0106] If the service attitude score is the first score, the service attitude of the service personnel is determined to be the first attitude; if the service attitude score is the second score, the service attitude of the service personnel is determined to be the second attitude; if the service attitude score is the third score, the service attitude of the service personnel is determined to be the third attitude; if the service attitude score is the fourth score, the service attitude of the service personnel is determined to be the fourth attitude; if the service attitude score is the fifth score, the service attitude of the service personnel is determined to be the fifth attitude;

[0107] The first score, the second score, the third score, the fourth score and the fifth score decrease in sequence, and the first attitude, the second attitude, the third attitude, the fourth attitude and the fifth attitude become worse in sequence.

[0108] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0109] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 400 of this embodiment includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program 421 that can be run on the processor 410. When the processor 410 executes the computer program 421, the steps in any of the above method embodiments are implemented, for example Figure 2 Alternatively, when the processor 410 executes the computer program 421, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 3 Functions of modules 301 to 303 are shown.

[0110] Exemplarily, the computer program 421 may be divided into one or more modules / units, one or more modules / units are stored in the memory 420, and are executed by the processor 410 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 421 in the electronic device 400.

[0111] Those skilled in the art will understand that Figure 4 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0112] The processor 410 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0113] The memory 420 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device, or an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. The above-mentioned memory 420 may also include both an internal storage unit of the electronic device and an external storage device. The above-mentioned memory 420 is used to store computer programs and other programs and data required by the electronic device. The memory 420 may also be used to temporarily store data that has been output or is to be output.

[0114] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0115] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for identifying the service attitude of hotel service personnel is implemented.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0122] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for identifying the service attitude of hotel service personnel, characterized in that: include: Acquire the service speech between the hotel service staff and the customer when the hotel service staff provides service to the customer, as well as the corresponding speech scene type; Input the speech scene type and the service speech into a trained target model, and obtain a service attitude score of the service personnel output by the target model; wherein the target model includes multiple modules, different modules correspond to different speech scene types, and different modules are trained based on multiple historical service voices and corresponding historical service attitude scores under corresponding speech scene types; The service attitude of the service personnel is determined according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

2. The method for identifying the service attitude of hotel service personnel according to claim 1, characterized in that: Before inputting the speech scene type and the service speech into a trained target model to obtain a service attitude score of the service personnel output by the target model, the method further includes: Obtain multiple historical service voices and historical service attitude scores corresponding to different service personnel, as well as the voice scene type corresponding to each historical service voice; By using historical service voices under different voice scene types and corresponding historical service attitude scores, each module of the target model is trained respectively to obtain a trained target model.

3. The hotel service staff service attitude recognition method according to claim 2, characterized in that: The method uses the historical service voices under different voice scene types and the corresponding historical service attitude scores to train each module of the target model to obtain a trained target model, including: For each type of speech scene type, input the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the predicted score output by the module; according to the predicted score and the historical service attitude score corresponding to the historical service speech, adjust the module corresponding to the type of speech scene type in the target model; Based on the adjusted modules, a trained target model is obtained.

4. The method for identifying the service attitude of hotel service personnel according to claim 3, characterized in that: For each type of voice scene type, adjusting the module corresponding to the type of voice scene type in the target model according to the predicted score and the historical service attitude score corresponding to the historical service voice includes: Determining an error value based on a difference between the predicted score and a historical service attitude score corresponding to the historical service speech; Determine whether the error value is greater than a preset threshold; If the error value is greater than the preset threshold, the module corresponding to the type of speech scene type in the target model is adjusted, and based on the module corresponding to the type of speech scene type in the adjusted target model, the step of inputting the historical service speech under the type of speech scene type into the module corresponding to the type of speech scene type in the target model to obtain the prediction score output by the module is re-executed until the error value is less than or equal to the preset threshold.

5. The method for identifying the service attitude of hotel service personnel according to any one of claims 1 to 4, characterized in that: Obtaining the voice scene type includes: Acquire the location information of the service personnel when the service personnel is providing service to the customer; the location information includes the WiFi information of the WiFi device to which the recording device carried by the service personnel is connected, and the recording device is used to record the service voice; Determine a corresponding WiFi device according to the WiFi information; The voice scene type is determined based on an installation location of the WiFi device.

6. The method for identifying the service attitude of hotel service personnel according to any one of claims 1 to 4, characterized in that: Obtaining the voice scene type includes: Inputting the service speech into a trained scene recognition model to obtain the speech scene type output by the scene recognition model; The scene recognition model is obtained based on a plurality of historical service voice trainings under different voice scene types.

7. The method for identifying the service attitude of hotel service personnel according to any one of claims 1 to 4, characterized in that: Determining the service attitude of the service personnel according to the service attitude score includes: If the service attitude score is the first score, the service attitude of the service personnel is determined to be the first attitude; if the service attitude score is the second score, the service attitude of the service personnel is determined to be the second attitude; if the service attitude score is the third score, the service attitude of the service personnel is determined to be the third attitude; if the service attitude score is the fourth score, the service attitude of the service personnel is determined to be the fourth attitude; if the service attitude score is the fifth score, the service attitude of the service personnel is determined to be the fifth attitude; The first score, the second score, the third score, the fourth score and the fifth score decrease in sequence, and the first attitude, the second attitude, the third attitude, the fourth attitude and the fifth attitude become worse in sequence.

8. A device for identifying the service attitude of hotel service personnel, characterized in that: include: An acquisition module, used to acquire the service speech between the hotel service staff and the customer when the hotel service staff provides service to the customer, and the corresponding speech scene type; A module is provided for inputting the speech scene type and the service speech into a trained target model to obtain a service attitude score of the service personnel output by the target model; wherein the target model includes a plurality of modules, different modules correspond to different speech scene types, and different modules are trained based on a plurality of historical service voices and corresponding historical service attitude scores under the corresponding speech scene types; A determination module is used to determine the service attitude of the service personnel according to the service attitude score; wherein the service attitude is positively correlated with the service attitude score.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the method for identifying the service attitude of hotel service personnel as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying the service attitude of hotel service personnel as described in any one of claims 1 to 7 is implemented.

Images