Method, device and storage medium for matching psychological counseling services to users

Abstract

The embodiment of the present invention relates to a method, device and storage medium for matching psychological counseling services for users. The method includes obtaining user attribute information and psychological counseling service attribute information based on a user list and a psychological counselor list; obtaining user training prompts and psychological counseling service training prompts based on the user attribute information and psychological counseling service attribute information; extracting user feature information and psychological counseling service feature information based on the user training prompts and psychological counseling service training prompts through a first language model; and matching the user feature information and psychological counseling service feature information through a second language model to obtain matching degree information between the user and the psychological counseling service. Thus, the efficiency and accuracy of psychological counseling services can be effectively improved.

Description

Technical Field

[0001] Embodiments of the present invention generally relate to the field of computers, and more specifically to a method, device, and storage medium for matching psychological counseling services to users. Background Art

[0002] Traditional methods for matching psychological counseling services to visitors (users) include, for example, calculating the matching degree based on predetermined indicators, parameters, etc.; performing simple matching based on keywords; recommending counselors through psychological staff, etc.

[0003] The above-mentioned traditional methods for matching psychological counseling services to visitors (users) all have shortcomings. One of them is that the matching degree is calculated through predetermined indicator parameters, which are dependent on the indicator parameters. Once there is a problem with the indicator parameter modeling, it is difficult to obtain accurate results. In the field of psychological counseling, it is difficult to calculate through indicator parameters due to the influence of the physical and mental state of the visitors (users) and the interview topics. On the other hand, the manual recommendation method is inefficient and it is difficult to make an appointment with a psychological counselor with a high matching degree in time. Simple matching based on keywords is difficult to obtain accurate matching results.

[0004] In summary, the traditional method of matching psychological counseling services to users has the following shortcomings: low efficiency and difficulty in obtaining accurate matching results. Summary of the invention

[0005] In response to the above problems, the present invention provides a method, device and storage medium for matching psychological counseling services for users, which can effectively improve the efficiency of matching psychological counseling services for visitors (users) and improve the matching accuracy.

[0006] According to a first aspect of the present invention, a method for matching psychological counseling services for users is provided, comprising: obtaining user attribute information and psychological counseling service attribute information based on a user list and a psychological counselor list, respectively; obtaining training prompts for the user and training prompts for the psychological counseling service based on the user attribute information and the psychological counseling service attribute information, respectively; extracting feature information of the user and feature information of the psychological counseling service based on the training prompts for the user and the training prompts for the psychological counseling service, respectively, via a first language model, wherein the feature information of the user includes feature labels of multiple dimensions of the user, and the feature information of the psychological counseling service includes feature labels of multiple dimensions of the psychological counselor; and matching the feature information of the user and the feature information of the psychological counseling service via a second language model to obtain matching information between the user and the psychological counseling service.

[0007] According to a second aspect of the present invention, a computing device is provided, comprising: at least one processing unit; at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to the first aspect.

[0008] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a machine, the method according to the first aspect is implemented.

[0009] According to a fourth aspect of the present invention, there is further provided a computer program product, comprising a computer program, wherein when the computer program is executed by a machine, the method of the first aspect of the present invention is performed.

[0010] In some embodiments, obtaining user attribute information and psychological counseling service attribute information includes: based on a user list and a psychological counselor list, respectively obtaining multi-dimensional information of the user and multi-dimensional information of the psychological counselor; and respectively performing data cleaning on the obtained multi-dimensional information of the user and multi-dimensional information of the psychological counselor, and standardizing them based on a predetermined data format, so as to respectively obtain user attribute information and psychological counseling service attribute information.

[0011] In some embodiments, the user's multi-dimensional information includes at least: basic information, family information, occupational information, educational background information, physiological condition information, psychological assessment information and historical consultation information; the psychological counselor's multi-dimensional information includes at least: basic information, professional experience information, consultation topic information, consultation style information, historical consultation information and historical satisfaction information.

[0012] In some embodiments, based on user attribute information and psychological counseling service attribute information, respectively obtaining training prompts for users and training prompts for psychological counseling services includes: based on user attribute information and psychological counseling service attribute information, respectively extracting training sentences of users related to the user's counseling topic, population type, work environment, emotional state, physiological indicators and psychological indicators through a first language model, and extracting training sentences of psychological counseling services related to the psychological counselor's professional experience, counseling topics, historical satisfaction information, and multi-dimensional information of users in historical counseling information; and performing at least one round of iterations based on training sentences of multiple users and training sentences of multiple psychological counseling services through the first language model to obtain training prompts for each user and training prompts for each psychological counselor.

[0013] In some embodiments, extracting the characteristic information of the user and the characteristic information of the psychological counseling service respectively based on the training prompts of the user and the training prompts of the psychological counseling service via the first language model includes: training the first language model through the acquired training prompts of the user and the training prompts of the psychological counseling service to generate multiple characteristic label types about the user and / or the psychological counselor; based on the generated multiple characteristic label types, feature labeling is performed for each user and each psychological counselor via the first language model to generate the characteristic labeling information of the user and the characteristic labeling information of the psychological counselor; and storing the characteristic labeling information of the user and the characteristic labeling information of the psychological counselor in the user characteristic database and the psychological counselor characteristic database respectively.

[0014] In some embodiments, matching the feature information of the user with the feature information of the psychological counseling service via a second language model to obtain the matching information between the user and the psychological counseling service includes: performing multiple rounds of iterations based on the feature annotation information of the user and the feature annotation information of the psychological counselor via the second language model to analyze the matching relationship between the feature labels of the user and the feature labels of the psychological counselor; and calculating the matching degree of the user and the psychological counselor based on the matching relationship and a predetermined feature type weight to obtain the matching score of the user and the psychological counselor.

[0015] In some embodiments, the method for matching psychological counseling services to users also includes: in response to receiving a counseling appointment request from a target user, obtaining the counseling topic type of the counseling appointment request, and extracting feature annotation information of the target user from a user feature database; generating, via a second language model, a matching score for the psychological counselor for the counseling appointment request of the target user based on the feature annotation information of the target user, the counseling topic type of the counseling appointment request, and a psychological counselor feature database; and recommending a psychological counselor to the target user based on the generated matching score for the psychological counselor for the counseling appointment request.

[0016] In some embodiments, the method for matching psychological counseling services to users also includes: extracting psychological counseling service satisfaction information based on feedback information from target users; and training the first language model and / or the second language model based on the extracted satisfaction information to optimize at least one of the user's training prompts, psychological counseling service training prompts, feature label types, feature annotations, and feature type weights.

[0017] In some embodiments, the feature label type includes at least two of the following types: a consulting topic feature, which is used to indicate that the type of consulting topic is emotional distress, mental health, interpersonal relationship, major stress, marriage and family, parent-child relationship, work-related and / or addictive behavior; a work environment feature, which is used to indicate that the user's work environment is high-risk, high-pressure, fast-paced, highly confrontational, high-communication, high-frequency business trips and / or long working hours; a special population feature, which is used to indicate that the user has a physical disability, a history of mental illness, gender identity disorder, a serious physical illness and / or is a pregnant woman; a special behavior feature, which is used to indicate that the user has recent self-harm behavior, hurts others, has a record of psychological counseling, frequently seeks medical treatment and / or has addictive behavior; Physiological abnormality characteristics are used to indicate that the user has insomnia, abnormal heart rate, sub-health, metabolic syndrome, abnormal blood sugar, abnormal blood pressure and / or abnormal digestive function; psychological abnormality characteristics are used to indicate that the user has a psychological state of high pressure, anxiety, tension, fatigue, loneliness, isolation, irritability and / or mania; demographic characteristics are used to indicate the user's age, gender, group and / or region; consulting style characteristics are used to indicate whether the counselor's style type is logical, intuitive, rational and / or emotional; satisfaction characteristics are used to indicate the counselor's historical counseling satisfaction score; and professional experience characteristics are used to indicate the counselor's work experience, professional title and / or professional level.

[0018] Therefore, in the scheme of the present invention, based on the user list and the psychological counselor list, user attribute information and psychological counseling service attribute information can be obtained respectively; based on the user attribute information and the psychological counseling service attribute information, the user's training prompts and the psychological counseling service's training prompts can be obtained respectively; through the first language model, based on the user's training prompts and the psychological counseling service's training prompts, the user's feature information and the psychological counseling service's feature information are extracted respectively; wherein, the user's feature information includes feature labels of multiple dimensions of the user, and the psychological counseling service's feature information includes feature labels of multiple dimensions of the psychological counselor, thereby realizing the extraction of features of multiple dimensions of the user and the psychological counselor through the first language model, making the feature extraction process visualized, and the extracted feature labels are all readable and visible, rather than vector expressions that are not readable by language.

[0019] Therefore, the present invention also matches the characteristic information of the user and the characteristic information of the psychological counseling service through the second language model to obtain the matching degree information between the user and the psychological counseling service; thereby, a more accurate matching result between the user and the psychological counselor can be obtained. Therefore, the present invention can effectively improve the efficiency and accuracy of matching the psychological counseling service for the visitor (user), and the recommendation process is more readable and visual, so that the psychological counselor, the prompt language engineer input by the language model, the relevant research and development personnel, etc., can optimize the characteristic labels in the recommendation process more directly, intuitively and efficiently, which is convenient for the optimization of the recommendation model, thereby obtaining a more accurate and efficient psychological counseling service provision result.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements.

[0022] Figure 1 A schematic diagram of a system for implementing a method for matching psychological counseling services to users according to an embodiment of the present invention is shown.

[0023] Figure 2 A flow chart of a method for matching psychological counseling services to users according to an embodiment of the present invention is shown.

[0024] Figure 3 A flow chart of a method for acquiring training prompts according to an embodiment of the present invention is shown.

[0025] Figure 4 A flow chart of a method for extracting characteristic information of a user and a psychological counselor according to an embodiment of the present invention is shown.

[0026] Figure 5 A flow chart of a method for obtaining matching information between a user and a psychological counseling service according to an embodiment of the present invention is shown.

[0027] Figure 6 A data flow diagram showing a process of matching a user with a psychological counseling service according to an embodiment of the present invention is shown.

[0028] Figure 7 A block diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0031] As described above, traditional methods for matching psychological counseling services to visitors (users) have shortcomings. For example, matching degree calculations based on predetermined indicators and parameters are dependent on indicator parameters. Once there is a problem with the indicator parameter modeling, it is difficult to obtain accurate results. In the field of psychological counseling, it is difficult to calculate through indicator parameters due to the influence of the physical and mental state of the visitors (users) and the interview topics. For example, manual recommendations are inefficient and it is difficult to make an appointment with a psychological counselor with a high matching degree in a timely manner. For example, simple matching based on keywords is difficult to obtain accurate matching results.

[0032] In summary, the traditional method of matching psychological counseling services to users has the following shortcomings: low efficiency and difficulty in obtaining accurate matching results.

[0033] In order to at least partially solve one or more of the above-mentioned problems and other potential problems, an exemplary embodiment of the present invention proposes a scheme for matching psychological counseling services for users. In the scheme of the present invention, based on a user list and a psychological counselor list, user attribute information and psychological counseling service attribute information can be obtained respectively; based on the user attribute information and the psychological counseling service attribute information, the user's training prompts and the psychological counseling service's training prompts can be obtained respectively; through a first language model, based on the user's training prompts and the psychological counseling service's training prompts, the user's feature information and the psychological counseling service's feature information are extracted respectively; wherein, the user's feature information includes feature labels of multiple dimensions of the user, and the feature information of the psychological counseling service includes feature labels of multiple dimensions of the psychological counselor, thereby realizing the extraction of multiple dimensional features of the user and the psychological counselor through the first language model, making the feature extraction process visualized, and the extracted feature labels are all readable and visible, rather than vector expressions that are not readable by language.

[0034] In addition, the present invention also matches the characteristic information of the user and the characteristic information of the psychological counseling service through the second language model to obtain the matching degree information between the user and the psychological counseling service; thereby, a more accurate matching result between the user and the psychological counselor can be obtained. Therefore, the present invention can effectively improve the efficiency and accuracy of matching psychological counseling services for visitors (users), and the recommendation process is more readable and visual, so that psychological counselors, prompt engineers input by the language model, related research and development personnel, etc. can optimize the characteristic labels in the recommendation process more directly, intuitively and efficiently, which is convenient for the optimization of the recommendation model, thereby obtaining more accurate and efficient psychological counseling service provision results.

[0035] Figure 1 FIG. 1 is a schematic diagram of a system 100 for implementing a method for matching psychological consulting services to users according to an embodiment of the present invention. Figure 1 As shown in FIG, system 100 includes computing device 110, server 130, network 140 and terminal device 150. Computing device 110, server 130 and terminal device 150 can exchange data through network 140 (e.g., the Internet, local area network, wired communication link, wireless communication link, optical fiber, cable, etc.).

[0036] The terminal device 150 may be a hardware device or software that supports network connection for data interaction and data processing. For example, it may be a mobile device, a personal terminal, a desktop, a smart watch, a tablet computer, an interactive device, etc. Users or psychological counselors can perform interactive operations on its display interface (such as inputting psychological counseling service consultation information, selecting topic types, entering attribute information, entering professional experience information, etc.), and the terminal device 150 exchanges data with the server 130 through the network.

[0037] Regarding the server 130, it can be, for example, an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud database, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and big data and artificial intelligence platforms. The server 130 can provide a variety of services, for example, obtaining psychological counseling service requirements input by users through the terminal device 150, such as psychological counselor appointment requests, counseling topics, user attribute information, demographic information, psychological state information, physiological state information, etc.; for example, psychological counselors input counselor attribute information, counseling style information, work experience, professional title information, working time information, etc. through the terminal device 150.

[0038] Regarding server 130, a method for matching psychological counseling services to users according to an embodiment of the present invention is deployed thereon, which can, for example, obtain user attribute information and psychological counselor attribute information through network 140, and send the extracted attribute information to computing device 110 for extracting feature labels of the user and the psychological counselor, so as to extract feature information of the user and feature information of the psychological counseling service, and match the feature information of the user and the feature information of the psychological counseling service to obtain matching information between the user and the psychological counseling service, and train the network, model, system, etc. provided by the embodiment of the present invention for the method for matching psychological counseling services to users.

[0039] Regarding the computing device 110, it is used, for example, to train the network model of the method for matching psychological counseling services for users according to an embodiment of the present invention, for example, the method for matching psychological counseling services for users according to an embodiment of the present invention is deployed thereon. The computing device 110 may have one or more processing units, including dedicated processing units such as GPU, FPGA and ASIC, and general processing units such as CPU. The computing device 110 may be an integration of multiple physical servers, an integration of multiple processing units, etc. In addition, one or more virtual machines may also be running on each computing device 110. In some embodiments, the computing device 110 and the server 130 may be integrated together, or they may be separately arranged from each other. In some embodiments, the computing device 110, for example, includes an attribute information acquisition module 112, a prompt acquisition module 114, a multidimensional feature extraction module 116, and a feature matching module 118.

[0040] The attribute information acquisition module 112 is used to respectively acquire user attribute information and psychological counseling service attribute information based on the user list and the psychological counselor list.

[0041] The prompt acquisition module 114 is used to respectively acquire the training prompts of the user and the training prompts of the psychological counseling service based on the user attribute information and the psychological counseling service attribute information.

[0042] Regarding the multi-dimensional feature extraction module 116, it is used to extract the user's feature information and the psychological counseling service's feature information respectively based on the user's training prompts and the psychological counseling service's training prompts via the first language model. The user's feature information includes the user's feature labels of multiple dimensions, and the feature information of the psychological counseling service includes the psychological counselor's feature labels of multiple dimensions.

[0043] The feature matching module 118 is used to match the feature information of the user with the feature information of the psychological counseling service via the second language model to obtain the matching degree information between the user and the psychological counseling service.

[0044] Figure 2 FIG. 2 is a flow chart of a method 200 for matching psychological consulting services to users according to an embodiment of the present invention. Figure 1 The computing device 110 shown may also be executed in Figure 7 The method 200 is executed at the electronic device 700. It should be understood that the method 200 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0045] In step 202, the computing device 110 obtains user attribute information and psychological counseling service attribute information based on the user list and the psychological counselor list, respectively.

[0046] In some embodiments, obtaining user attribute information and psychological counseling service attribute information includes: based on a user list and a psychological counselor list, respectively obtaining multi-dimensional information of the user and multi-dimensional information of the psychological counselor; and respectively performing data cleaning on the obtained multi-dimensional information of the user and multi-dimensional information of the psychological counselor, and standardizing them based on a predetermined data format, so as to respectively obtain user attribute information and psychological counseling service attribute information.

[0047] For example, the user list contains various attribute information about the user, such as but not limited to the user's age, gender, occupation, physical condition information, medical records, psychological state information, educational background information, etc.; the psychological counselor list contains attribute information about the psychological counselors, such as but not limited to the psychological counselor's work experience, consulting style, satisfaction score, working hours, etc.

[0048] Regarding data cleaning and standardization based on a predetermined data format, for example, eliminating noise, outliers, missing values, etc. in the data, so as to ensure the accuracy and standardization of the multi-dimensional information obtained subsequently, and also help with the generation of prompts and the extraction of features.

[0049] In some embodiments, the user's multi-dimensional information includes at least: basic information, family information, occupational information, educational background information, physiological status information, psychological assessment information and historical consultation information.

[0050] In some embodiments, the multi-dimensional information of the psychological counselor includes at least: basic information, professional experience information, information on counseling topics that the counselor is good at, counseling style information, historical counseling information, and historical satisfaction information.

[0051] Regarding the predetermined data format, for example, the multi-dimensional information of the user and the multi-dimensional information of the psychological counselor are displayed in the form of archives, the format of predetermined data files, etc. The following illustrates a display form of the multi-dimensional information of the user, but is not limited to this.

[0052] Basic Information: - Name: [employee’s full name], - Gender: [Male / Female], - Age: [specific age], - Position: [Detailed Position], - Department: [Department Name], - Date of joining: [year / month / day], - Contact information: [phone number / email address]; Family Information: - Marital status: [married, single, divorced, etc.], - Spouse information (if any): - Name: [spouse’s full name], - Occupation: [specific job], - Health status: [good, suffering from a certain disease, etc.], - Children's information (if any): - Number of children: [e.g. 2], - Age and gender: [e.g. son is 10 years old, daughter is 7 years old], - Academic status: [excellent, good, average, etc.], - Family member relationships: [overall evaluation such as harmony, tension, etc.], - Major family events (in the past year): [such as serious illness of family members, house purchase, financial crisis, etc.]; Psychological Assessment Information: - Assessment Date: [date of most recent assessment], - Assessment tools: [e.g. MMPI, 16PF, etc.], - Evaluation result label: - Emotional state: [such as stable, anxious tendency, depressed tendency, etc.], - Interpersonal relationships: [good, tense, lonely, etc.], - Stress coping: [positive, negative, moderate], - Total score and grade: [specific score and corresponding grade, such as excellent, good, need attention, etc.]; Psychological consultation records (if any): - Consultation date: [the time of each consultation], - Consultant: [Consultant’s name], - Question Tags: - Work pressure: [such as heavy workload, difficult tasks, long working hours, etc.], - Interpersonal conflicts: [Conflicts with colleagues, superiors or subordinates], - Career development: [promotion bottlenecks, career planning confusion, etc.], - Emotional distress: [anxiety, depression, irritability and other emotional problems]; - Consulting suggestions: - Short-term relief measures: [such as deep breathing training, temporarily adjusting work pace, etc.], - Long-term coping strategies: [such as communication skills training, career planning guidance, etc.];…

[0053] In step 204, the computing device 110 obtains the training prompts of the user and the training prompts of the psychological counseling service respectively based on the user attribute information and the psychological counseling service attribute information.

[0054] Please refer to the attached Figure 6 The data flow diagram of the matching process between users and psychological counseling services in an embodiment of the present invention is illustrated. After obtaining the user list 611 and the psychological counselor list 621, the two lists are processed respectively to obtain the multi-dimensional information 612 of the user and the multi-dimensional information 622 of the psychological counselor, and the data is cleaned and the format is standardized to generate the user attribute information 613 and the psychological counseling service attribute information 623; then the user's training prompt 614 and the psychological counseling service training prompt 624 are generated respectively. It should be understood that the generation of training prompts can be achieved through a large language model, or through user feedback and operational feedback from prompt engineers, that is, the generation of training prompts can be adjusted in combination with artificial intelligence and feedback from professionals, so as to obtain more accurate training prompts.

[0055] The following will combine Figure 3 The method for obtaining the training prompt in the embodiment of the present invention is described in detail, which will not be repeated here.

[0056] In step 206, the computing device 110 extracts the characteristic information of the user and the characteristic information of the psychological counseling service respectively based on the training prompts of the user and the training prompts of the psychological counseling service via the first language model, wherein the characteristic information of the user includes characteristic labels of multiple dimensions of the user, and the characteristic information of the psychological counseling service includes characteristic labels of multiple dimensions of the psychological counselor.

[0057] Please continue to refer to Figure 6 , the user's training prompts 614 and the psychological counseling service training prompts 624 are respectively input into the first language model 63, so as to extract multi-dimensional feature labels. It should be understood here that the first language model can extract multiple feature labels based on the commonalities and individualities between the user's multi-dimensional data and the psychological counselor's multi-dimensional data. These feature labels can reflect the common features between users, the common features between psychological counselors, and the common features between psychological counselors and users.

[0058] Regarding the first language model, such as the GPT series language model (ChatGPT), BERT model, Wenxinyiyan model, ChatGLM model, Grok model, ERNIE model, etc.

[0059] The following will combine Figure 4 The method for extracting characteristic information of users and psychological counselors according to an embodiment of the present invention is described in detail and will not be repeated here.

[0060] In step 208 , the computing device 110 matches the characteristic information of the user with the characteristic information of the psychological counseling service via the second language model to obtain matching information between the user and the psychological counseling service.

[0061] Please continue to refer to Figure 6 After passing through the first language model 63, the characteristic information 616 of the user and the characteristic information 626 of the psychological counseling service can be obtained respectively, and the characteristic information 616 of the user and the characteristic information 626 of the psychological counseling service are input into the second language model 64 for matching, so as to obtain the matching degree information 600 between the user and the psychological counseling service, and provide the user with psychological counseling services according to the matching degree information 600, for example, according to the matching degree score between the psychological counselor and the user, recommend a psychological counselor with a higher matching degree to the user.

[0062] Regarding the second language model, such as the GPT series of language models (ChatGPT), BERT model, Wenxinyiyan model, ChatGLM model, Grok model, ERNIE model, etc.

[0063] In addition, the first language model and the second language model may be models of the same type or models of different types. They may be the same model of the same type or two different models of the same type.

[0064] The following will combine Figure 5 The method for obtaining matching information between a user and a psychological counseling service according to an embodiment of the present invention is described in detail, which will not be repeated here.

[0065] In the above scheme, user attribute information and psychological counseling service attribute information are obtained from the user list and the psychological counselor list (these attribute information respectively contain multiple dimensions of information of the user and the psychological counselor); and through the first language model, multiple dimensions of features of the user and the psychological counselor are extracted, so that the feature extraction process is visualized. The extracted feature labels cover information of multiple dimensions, and because they are obtained based on the language model, the feature labels are readable and visible, rather than vector expressions that are unreadable by language. This also helps the feature labels and training prompts receive manual feedback information for adjustment.

[0066] In the above scheme, the second language model is also used to match the user's feature information with the feature information of the psychological counseling service to obtain the matching information between the user and the psychological counseling service; thus, a more accurate matching result between the user and the psychological counselor can be obtained; thus. It can effectively improve the efficiency and accuracy of matching the psychological counseling service for the visitor (user), and the recommendation process is more readable and visual, so that the psychological counselor, the prompt engineer of the language model input, the relevant R&D personnel, etc. can optimize the feature labels in the recommendation process more directly, intuitively and efficiently, which is convenient for the optimization of the recommendation model, so as to obtain more accurate and efficient psychological counseling service provision results.

[0067] Figure 3 FIG. 3 is a flow chart of a method 300 for obtaining training prompts according to an embodiment of the present invention. The method 300 may be performed as follows: Figure 1 The computing device 110 shown may also be executed in Figure 7 The method 300 is executed at the electronic device 700 shown. It should be understood that the method 300 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0068] In step 302, the computing device 110 extracts, via the first language model, training sentences of the user related to the user's consulting topic, population type, work environment, emotional state, physiological indicators, and psychological indicators, based on the user attribute information and the psychological counseling service attribute information, and extracts training sentences of the psychological counseling service related to the psychological counselor's professional experience, consulting topics, historical satisfaction information, and multi-dimensional information of the user in historical counseling information.

[0069] For example, the types of consulting topics include emotional distress, mental health, interpersonal relationships, major stress, marriage and family, parent-child relationships, work-related and / or addictive behaviors; for example, the work environment includes high risk, high pressure, fast pace, strong confrontation, high communication, high frequency of business trips and / or long working hours; for example, the type of population has special population characteristics, including those with physical disabilities, history of mental illness, gender identity disorder, serious physical illness and / or pregnant women; for example, special behaviors include users' recent self-harm behaviors, harming others, psychological counseling records, frequent medical treatment and / or addictive behaviors; for example, abnormal physiological characteristics , including the user's insomnia, abnormal heart rate, sub-health, metabolic syndrome, abnormal blood sugar, abnormal blood pressure and / or abnormal digestive function; for example, abnormal psychological characteristics, including the user's high pressure, anxiety, tension, fatigue, loneliness, isolation, irritability and / or mania; for example, demographic characteristics, including the user's age, gender, group and / or region; for example, consulting style characteristics, including the counselor's style type is logical, intuitive, rational and / or emotional; for example, professional experience characteristics, including the counselor's work experience, title and / or professional level.

[0070] In step 304, the computing device 110 performs at least one round of iterations via the first language model based on the training sentences of multiple users and the training sentences of multiple psychological counseling services, so as to obtain training prompts for each user and training prompts for each psychological counselor.

[0071] Regarding obtaining training prompts for each user and training prompts for each psychological counselor, for example, training prompts for the 100 users in the user list are obtained respectively. The training prompts for each user are extracted based on the attribute information of the user, and the training prompts for each psychological counselor are also extracted based on the attribute information of the user.

[0072] In some embodiments, at least one round of iteration is performed via the first language model to obtain training prompts for each user and training prompts for each psychological counselor, and further includes: in response to feedback from users and prompt engineers, the first language model adjusts the prompt generation strategy so that in the next round of iteration, a different training prompt is generated for the same user. It should be understood that the same adjustment and iteration can also be performed for the prompts of the psychological counselors.

[0073] Therefore, through the above scheme, after multiple rounds of iterations, the training prompts of the user and the training prompts of the psychological counselor can fully reflect the multi-dimensional information of the user and the psychological counselor, and can adjust the prompt generation of the first language model in combination with the feedback information of the user and professionals (such as prompt engineers, psychological counselors, etc.), so as to obtain more accurate training prompts.

[0074] Figure 4 FIG. 4 is a flowchart of a method 400 for extracting characteristic information of a user and a psychological counselor according to an embodiment of the present invention. Figure 1 The computing device 110 shown may also be executed in Figure 7 The method 400 is executed at the electronic device 700. It should be understood that the method 400 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0075] In step 402, the computing device 110 trains the first language model by using the acquired training prompts of the user and the training prompts of the psychological counseling service, so as to generate a plurality of feature label types about the user and / or the psychological counselor.

[0076] It should be understood that one of the multiple feature label types can be only for users, only for psychological counselors, or can be applied to both users and psychological counselors. For example, feature labels related to professional experience are used for feature annotation of psychological counselors, labels related to special population features are used for feature annotation of users, labels related to work environment features are also used for feature annotation of users, and feature labels related to consulting style are used for feature annotation of psychological counselors; they are not listed one by one here.

[0077] In step 404, the computing device 110 performs feature annotation for each user and each psychological counselor via the first language model based on the generated multiple feature tag types, so as to generate feature annotation information of the user and feature annotation information of the psychological counselor.

[0078] In step 406 , the computing device 110 stores the user's feature annotation information and the psychological counselor's feature annotation information in the user feature database and the psychological counselor feature database, respectively.

[0079] Therefore, through the above scheme, the first language model extracts more standardized, common, and concise feature labels from these training prompts to perform feature annotation of users and / or psychological counselors; and through the above multiple feature label types, feature annotation can be completed for each user and each psychological counselor respectively to generate a user feature database and a psychological counselor feature database.

[0080] In some embodiments, the feature label type includes a counseling topic feature, which is used to indicate that the type of counseling topic is emotional distress, mental health, interpersonal relationships, major stress, marriage and family, parent-child relationships, work-related and / or addictive behavior.

[0081] In some embodiments, the feature tag type includes a work environment feature for indicating that the user's work environment is high risk, high pressure, fast pace, strong confrontation, high communication, high frequency of business trips and / or long working hours.

[0082] In some embodiments, the feature tag type includes special population features for indicating that the user has a physical disability, a history of mental illness, gender identity disorder, a serious physical illness, and / or is a pregnant woman.

[0083] In some embodiments, the feature tag type includes special behavioral features for indicating that the user has recently engaged in self-harming behaviors, harming others, psychological counseling records, frequent medical treatment, and / or addictive behaviors.

[0084] In some embodiments, the feature tag type includes physiological abnormality features, which are used to indicate that the user has insomnia, abnormal heart rate, sub-health, metabolic syndrome, abnormal blood sugar, abnormal blood pressure and / or abnormal digestive function.

[0085] In some embodiments, the feature tag type includes a psychological abnormality feature, which is used to indicate that the user has a psychological state of high pressure, anxiety, tension, fatigue, loneliness, isolation, irritability and / or mania.

[0086] In some embodiments, the feature tag type includes demographic features indicating the user's age, gender, group affiliation, and / or region.

[0087] In some embodiments, the feature label type includes a counseling style feature, which is used to indicate that the counselor's style type is logical, intuitive, rational, and / or emotional.

[0088] In some embodiments, the feature tag type includes a satisfaction feature that indicates the counselor's historical counseling satisfaction scores.

[0089] In some embodiments, the feature tag type includes a professional experience feature, which is used to indicate the work experience, job title and / or professional level of the psychological counselor.

[0090] Figure 5 FIG. 5 is a flow chart showing a method 500 for obtaining matching information between a user and a psychological counseling service according to an embodiment of the present invention. Figure 1 The computing device 110 shown may also be executed in Figure 7The method 500 is executed at the electronic device 700. It should be understood that the method 500 may further include additional steps not shown and / or may omit the steps shown, and the scope of the present invention is not limited in this respect.

[0091] In step 502, the computing device 110 performs multiple rounds of iterations based on the feature annotation information of the user and the feature annotation information of the psychological counselor via the second language model to analyze the matching relationship between the feature labels of the user and the feature labels of the psychological counselor.

[0092] In step 504, the computing device 110 performs a matching calculation between the user and the psychological counselor based on the matching relationship and the predetermined feature type weights, so as to obtain a matching score between the user and the psychological counselor.

[0093] Regarding the matching weights, for example, the weight of the consulting topic is 50%, the weight of the consultant's satisfaction is 10%, the weight of the consultant's years of work is 5%, and the weight of the consultant's gender is 10%. For example, based on the type of the predetermined user, the weights of multiple feature types are determined to calculate the matching degree between the user and the psychological counselor; the user type includes special population type, psychological abnormality feature type, physiological abnormality feature type, special behavior type, etc.; based on the user type, the weight of one or more feature types is increased or decreased. For example, for pregnant women in special populations, the weight of the consultant's gender is 20%, which is higher than that of other populations, and the weight of the style type is also appropriately increased. For example, for users with abnormal psychological characteristics, the weight of the consulting style type feature is also higher than that of other populations.

[0094] In step 506 , if the computing device 110 receives a consultation appointment request from a target user, it obtains the consultation topic type of the consultation appointment request and extracts feature annotation information of the target user from a user feature database.

[0095] In step 508, the computing device 110 generates a matching score for the psychological counselor of the target user's consultation appointment request based on the target user's feature annotation information, the consultation topic type of the consultation appointment request, and the psychological counselor feature database via the second language model.

[0096] At step 510 , the computing device 110 recommends a psychological counselor to the target user based on the matching scores of the psychological counselors generated regarding the consultation appointment request.

[0097] It is worth noting that the text information obtained from "user's multi-dimensional information → user attribute information → user's training prompts → user's multi-dimensional feature labels → user's feature information" has gone through a process from more to less, from complex to general, from chaotic to regular, and from random to common. Specifically, for example, the user's multi-dimensional information is composed of dozens or hundreds of pages of user profile information; and the user's attribute information contains the user's multi-dimensional information in a standardized format, for example, hundreds of pages of user profile information are refined into a few pages or dozens of pages; and to the user's training prompts, the user attribute information is further subjected to keyword extraction, combination, generation and reorganization, etc., to obtain a more concise prompt; and from the user's training prompts to feature annotation, the common features between users and psychological counselors are further extracted through the training prompts, and the feature annotation information of users and psychological counselors is performed through more concise words, phrases, short sentences and other features.

[0098] It should be understood that the process from “multi-dimensional information of psychological counselor → attribute information of psychological counseling service → training prompts for psychological counseling service → multi-dimensional feature labels of psychological counselor → feature information of psychological counseling service” also goes through similar or identical steps as above. Therefore, in the embodiment of the present invention, the process from “multi-dimensional information → attribute information → training prompts → multi-dimensional feature labels → feature information” goes through simplification and regular expression in language and text, and finally obtains visualized feature labels and feature attribute information, and uses a set of standardized feature labels to label features of different users and different psychological counselors, thereby discovering the matching relationship between different users and different psychological counselors, and thus obtaining more accurate and efficient matching results.

[0099] In some embodiments, it also includes: extracting psychological counseling service satisfaction information based on feedback information from target users; based on the extracted satisfaction information, training the first language model and / or the second language model to optimize at least one of the user's training prompts, psychological counseling service training prompts, feature label types, feature annotations, and feature type weights.

[0100] Regarding the optimization of feature label types, feature annotations, and feature type weights, these contents to be optimized are not specific to users or psychological counselors, but rather optimize the feature label types, feature annotations, and feature type weights of users and / or psychological counselors. They can be unique to users or psychological counselors, or they can be common features of both.

[0101] To further facilitate understanding of the solution, some examples are given below.

[0102] For example, visitor (user) S is matched with counselors A, B, C, and D.

[0103] Some attribute information of the client S: middle-aged woman, seeking consultation due to strained family relationships.

[0104] Characteristics of counselor A: Specializes in marriage and love relationships, family relationship counseling, is a national first-level psychological counselor, has many years of work experience and has rich experience in dealing with family relationship issues. The average satisfaction score of historical visitors on counselor A's family and marriage issues is 8.

[0105] The matching score obtained by counselor A is: 9 (high matching, the counselor’s professional field is highly relevant to the client’s problem, and the satisfaction score for this issue is high).

[0106] Characteristics of counselor B: Specializes in marriage and love relationships, family relationship counseling, is a national second-level psychological counselor, has many years of work experience and rich experience in dealing with family relationship issues. The average satisfaction score of historical visitors on counselor B's family and marriage issues is 7.

[0107] Counselor B’s matching score: 8 (high matching, the counselor’s professional field is highly relevant to the client’s problem, and the satisfaction score for this issue is high).

[0108] Characteristics of counselor C: Specializes in marriage and love relationship counseling, family relationship counseling, national second-level psychological counselor, has provided fewer consultations, and the average satisfaction score of historical clients on counselor C's family and marriage issues is 8.

[0109] Counselor C’s matching score: 7 (high matching, the counselor’s professional field is highly relevant to the client’s problem, and the satisfaction score for this issue is high).

[0110] Characteristics of counselor D: Good at marriage and family counseling, few years of working experience, national third-level psychological counselor, fewer consultations, and the average satisfaction score of historical clients on counselor D's family and marriage issues is 7.

[0111] Counselor D’s matching score: 6 (high matching, the counselor’s professional field is highly relevant to the client’s problem, and the satisfaction score for this issue is high).

[0112] Based on the above matching scores, psychological counselors A and B are recommended to visitor (user) S on a priority basis.

[0113] Figure 7 Schematic diagram of an example electronic device 700 that can be used to implement an embodiment of the present specification is shown. Figure 1The computing device 110 shown can be implemented by an electronic device 700. As shown, the electronic device 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 702 or computer program instructions loaded from a storage unit 708 to a random access memory (RAM) 703. In the random access memory 703, various programs and data required for the operation of the electronic device 700 can also be stored. The central processing unit 701, the read-only memory 702, and the random access memory 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0114] Multiple components in the electronic device 700 are connected to the input / output interface 705, including: an input unit 706, such as a keyboard, a mouse, a microphone, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The various processes and processing described above, such as methods 200 to 500, may be performed by the central processing unit 701. For example, in some embodiments, methods 200 to 500 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the read-only memory 702 and / or the communication unit 709. When the computer program is loaded into the random access memory 703 and executed by the central processing unit 701, one or more actions of the methods 200 to 500 described above may be performed.

[0116] The present invention relates to methods, apparatuses, systems, electronic devices, computer-readable storage media and / or computer program products. The computer program products may include computer-readable program instructions for executing various aspects of the present invention.

[0117] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0118] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge computing devices. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0119] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be executed by using the state information of the computer-readable program instructions to personalize and customize the electronic circuit, thereby implementing various aspects of the present invention.

[0120] Various aspects of the present invention are described herein with reference to flow charts and / or step diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each of the steps in the flow charts and / or step diagrams and the combination of the steps in the flow charts and / or step diagrams can be implemented by computer-readable program instructions.

[0121] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more steps in the flowchart and / or step diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more steps in the flowchart and / or step diagram.

[0122] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more steps in the flowchart and / or step diagram.

[0123] The flowchart and step diagram in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each square step in the flowchart or step diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square steps can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive square steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square step in the step diagram and / or the flowchart, and the combination of the square steps in the step diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for matching psychological counseling services to users, characterized in that: include: Based on the user list and the psychological counselor list, user attribute information and psychological counseling service attribute information are obtained respectively; Based on the user attribute information and the psychological counseling service attribute information, respectively obtaining the user's training prompt and the psychological counseling service's training prompt; Through the first language model, based on the user's training prompts and the psychological counseling service's training prompts, feature information of the user and feature information of the psychological counseling service are respectively extracted, wherein the user's feature information includes feature labels of multiple dimensions of the user, and the feature information of the psychological counseling service includes feature labels of multiple dimensions of the psychological counselor; as well as, The user's characteristic information and the psychological counseling service's characteristic information are matched via the second language model to obtain matching information between the user and the psychological counseling service.

2. The method according to claim 1, characterized in that Obtaining user attribute information and psychological counseling service attribute information includes: Based on the user list and the psychological counselor list, respectively obtain the multi-dimensional information of the user and the multi-dimensional information of the psychological counselor; and, The obtained multi-dimensional information of the user and the multi-dimensional information of the psychological counselor are cleaned and standardized based on a predetermined data format, so as to obtain user attribute information and psychological counseling service attribute information respectively.

3. The method according to claim 2, characterized in that The user's multi-dimensional information includes at least: basic information, family information, occupation information, educational background information, physiological status information, psychological assessment information and historical consultation information; The multi-dimensional information of a psychological counselor includes at least: basic information, professional experience information, information on counseling topics that the counselor is good at, counseling style information, historical counseling information, and historical satisfaction information.

4. The method according to claim 1, characterized in that: Based on the user attribute information and the psychological counseling service attribute information, respectively obtaining the user's training prompt and the psychological counseling service's training prompt includes: Based on the user attribute information and the psychological counseling service attribute information, the first language model is used to extract the user's training sentences related to the user's counseling topic, the type of people to whom the user belongs, the work environment, the emotional state, the physiological indicators and the psychological indicators, and the psychological counseling service training sentences related to the psychological counselor's professional experience, counseling topic, historical satisfaction information, and the multi-dimensional information of the user in the historical counseling information; and, Based on the training sentences of multiple users and the training sentences of multiple psychological counseling services, at least one round of iteration is performed via the first language model to obtain the training prompts for each user and the training prompts for each psychological counselor.

5. The method according to claim 4, characterized in that The first language model is used to extract the user's characteristic information and the psychological counseling service's characteristic information based on the user's training prompt and the psychological counseling service's training prompt, respectively, including: The first language model is trained by using the acquired training prompts of the user and the training prompts of the psychological counseling service to generate a plurality of feature label types about the user and / or the psychological counselor; Based on the generated multiple feature tag types, feature labeling is performed for each user and each psychological counselor via the first language model to generate feature labeling information of the user and feature labeling information of the psychological counselor; and, The user's feature annotation information and the psychological counselor's feature annotation information are stored in a user feature database and a psychological counselor's feature database respectively.

6. The method according to claim 5, characterized in that Through the second language model, the user's characteristic information and the characteristic information of the psychological counseling service are matched to obtain the matching degree information between the user and the psychological counseling service, including: By using the second language model, multiple rounds of iterations are performed based on the feature labeling information of the user and the feature labeling information of the psychological counselor, so as to analyze the matching relationship between the feature labels of the user and the feature labels of the psychological counselor; and Based on the matching relationship and the predetermined feature type weight, the matching degree between the user and the psychological counselor is calculated to obtain the matching degree score between the user and the psychological counselor.

7. The method according to claim 6, characterized in that Also includes: In response to receiving a consultation appointment request from a target user, obtaining a consultation topic type of the consultation appointment request, and extracting feature annotation information of the target user from a user feature database; Generate a matching score of the psychological counselor of the consultation appointment request of the target user based on the feature annotation information of the target user, the consultation topic type of the consultation appointment request, and a psychological counselor feature database through the second language model; as well as, Based on the generated matching scores of the psychological counselors for the consultation appointment request, a psychological counselor is recommended to the target user.

8. The method according to claim 6, characterized in that Also includes: Extract psychological counseling service satisfaction information based on target users’ feedback information; Based on the extracted satisfaction information, the first language model and / or the second language model is trained to optimize at least one of the user's training prompts, the psychological counseling service's training prompts, the feature label type, the feature annotation, and the feature type weight.

9. The method according to claim 5, characterized in that Feature tag types include at least two of the following types: Characteristics of counseling topics, used to indicate whether the type of counseling topic is emotional distress, mental health, interpersonal relationships, major stress, marriage and family, parent-child relationships, work-related, and / or addictive behavior; Work environment characteristics, used to indicate that the user's work environment is high risk, high pressure, fast pace, strong confrontation, high communication, high frequency of business trips and / or high working hours; Special population characteristics, used to indicate that the user has a physical disability, a history of mental illness, gender identity disorder, a serious physical illness, and / or is a pregnant woman; Special behavioral characteristics that indicate that the user has recently engaged in self-harm, harming others, has a history of psychological counseling, frequently seeks medical attention, and / or has addictive behavior; Physiological abnormality characteristics, used to indicate that the user has insomnia, abnormal heart rate, sub-health, metabolic syndrome, abnormal blood sugar, abnormal blood pressure and / or abnormal digestive function; Psychological abnormality characteristics, which are used to indicate that the user is in a state of high stress, anxiety, tension, fatigue, loneliness, isolation, irritability and / or mania; Demographic characteristics, which indicate the user's age, gender, group affiliation, and / or region; Counseling style characteristics are used to indicate whether the counselor's style type is logical, intuitive, rational, and / or emotional; Satisfaction characteristics, which indicate the counselor's historical counseling satisfaction scores; and, Professional experience characteristics are used to indicate the psychological counselor's work experience, professional title and / or professional level.

10. A computing device, characterized in that: include: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a machine, the method according to any one of claims 1 to 9 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a machine, the method according to any one of claims 1 to 9 is performed.

Images