Information optimization method for artificial intelligence and server

Abstract

The invention discloses an information optimization method for artificial intelligence and a server, and relates to the technical field of artificial intelligence, and the optimization method comprises the following steps: 1, obtaining the basic information of a user; 2, obtaining a user preference knowledge relationship network; 3, disassembling a local knowledge relationship chain of each preference knowledge relationship network; and step 4, combining the screened local knowledge relationship chains, in the method, a plurality of corresponding preference knowledge relationship networks are selected according to the user operation behavior information to open a screening range, so that the user operation behavior information can be most comprehensively screened; the screened local knowledge relation chains are combined, a new preference knowledge relation network is defined for the user, the new preference knowledge relation network is composed of the closest preference knowledge relation network and a plurality of local knowledge relation chains, and labels can be added to user operation behavior information while the current preference knowledge relation network is met, so that the user operation behavior information is identified. And subsequent user feature description upgrading is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an information optimization method and server for artificial intelligence. Background Art

[0002] Artificial intelligence is becoming more and more popular, especially in the Internet. Among them, the mainstream application of artificial intelligence is adjustment processing, such as combining existing algorithms to analyze user portraits or process behavioral preferences.

[0003] According to patent number CN116341660B, the patent name: information optimization method and server applied to artificial intelligence, which records "an information optimization method applied to artificial intelligence, applied to an information optimization server, the method comprising: obtaining user operation behavior information corresponding to the cloud service interaction event when generating a user portrait knowledge set for the cloud service interaction event; the user operation behavior information forms a behavior preference knowledge relationship network, the behavior preference knowledge relationship network includes a number of behavior preference knowledge members; combining the member connections of each active knowledge member among the several behavior preference knowledge members in the behavior preference knowledge relationship network, determining the relative relationship variables of the active knowledge members in the behavior preference knowledge relationship network; optimizing the behavior preference knowledge relationship network in combination with the relative relationship variables to obtain an optimized relationship network corresponding to the user operation behavior information", those skilled in the art can know that the patent first selects the relationship network through personal behavior actions, and then optimizes the relationship network through relationship network fission screening, but the method has the problem that if the initial relationship network positioning is wrong, it will cause the subsequent optimization to deviate, thereby affecting the analysis of personal portraits.

[0004] In summary, an information optimization method and server for artificial intelligence are designed. Summary of the invention

[0005] In order to overcome the above-mentioned deficiencies, the present invention provides an information optimization method and server for artificial intelligence.

[0006] The present invention achieves the above-mentioned purpose through the following technical solutions: An information optimization method for artificial intelligence, applied to an information optimization server, the optimization method comprising the following steps: Step 1: Obtain basic user information, where the basic information includes user operation behavior information corresponding to the cloud service interaction event and the user portrait of the cloud service interaction event; Step 2: Obtain the user preference knowledge relationship network, and select several corresponding preference knowledge relationship networks according to the user operation behavior information; Step 3: Disassemble the local knowledge relationship chains of each preference knowledge relationship network and select the local knowledge relationship chains that match the user operation behavior information; Step 4: Combine the selected local knowledge relationship chains to define a new preference knowledge relationship network for the user; Among them, in step 4, the new preference knowledge relationship network is composed of the closest preference knowledge relationship network plus several local knowledge relationship chains, and the new preference knowledge relationship network enters the database to upgrade the subsequent user feature description.

[0007] Preferably, in step three, the disassembled local knowledge relationship chain is matched with the user operation behavior information and the portrait, and the high similarity is used as the first description value, and the low similarity is used as the second description value.

[0008] Preferably, in step three, when the similarity of the disassembled local knowledge relationship chain is low, each local knowledge relationship chain in the preference knowledge relationship network associated with the local knowledge relationship chain continues to be matched with the user operation behavior information and portrait, and the high similarity is used as the second description value, and the low similarity is used as the third description value.

[0009] Preferably, in step four, if part of the user's operation behavior information exceeds the local knowledge relationship chain covered by the new preference knowledge relationship network, the new user operation behavior information enters step two, the user is re-characterized, and the new preference knowledge relationship network obtained covers a new preference knowledge relationship network.

[0010] An information optimization server includes a processor and a memory, the processor and the memory are communicatively connected, and the processor is used to read a computer program from the memory and execute it to implement the above method.

[0011] Preferably, the processor includes a power module, the power module includes a power circuit, the power circuit includes an integrated circuit, a first capacitor, a second capacitor, a third capacitor, a fourth capacitor, a battery, an electronic switch and a diode, the model of the integrated circuit is 78L24, the input end of the integrated circuit is grounded through the first capacitor and the second capacitor respectively, the output end of the integrated circuit is grounded through the third capacitor and the fourth capacitor respectively, the ground end of the integrated circuit is grounded, the input end of the integrated circuit is electrically connected to the negative electrode of the battery, the positive electrode of the battery is electrically connected to the output end of the integrated circuit through the electronic switch, the trigger end of the electronic switch is electrically connected to the cathode of the diode, the anode of the diode is electrically connected to the output end of the integrated circuit, the electronic switch is an IGBT, when the power circuit loses power, the internal circuit will generate a reverse voltage, thereby turning on the electronic switch through the diode, after the electronic switch is turned on, the battery can continue to output the power supply voltage to ensure that the power circuit outputs the working voltage.

[0012] The beneficial effects of the present invention are as follows: In the information optimization method and server for artificial intelligence: 1. First, by selecting a number of corresponding preference knowledge relationship networks according to the user's operation behavior information, the screening range can be opened, so that the user's operation behavior information can be screened most comprehensively; 2. Combine the selected local knowledge relationship chains to define a new preference knowledge relationship network for the user. The new preference knowledge relationship network is composed of the closest preference knowledge relationship network plus several local knowledge relationship chains. While conforming to the current preference knowledge relationship network, it can also add tags to the user's operation behavior information to facilitate subsequent user feature description upgrades; 3. The power supply circuit uses the characteristic that reverse voltage will be generated when the circuit loses power to trigger the electronic switch to turn on, so that the processor can continue to be powered by the internal battery when the external power is lost, thereby improving the stability of the entire server operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will now be described by way of example with reference to the accompanying drawings, in which: Figure 1 is a system block diagram of the present invention; Figure 2 It is a circuit principle diagram of the power supply circuit of the present invention. DETAILED DESCRIPTION

[0014] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0015] like Figure 1 As shown, an information optimization method for artificial intelligence is applied to an information optimization server, and the optimization method comprises the following steps: Step 1: Obtain basic user information, where the basic information includes user operation behavior information corresponding to the cloud service interaction event and the user portrait of the cloud service interaction event; Step 2: Obtain the user preference knowledge relationship network, and select several corresponding preference knowledge relationship networks according to the user operation behavior information; Step 3: Disassemble the local knowledge relationship chains of each preference knowledge relationship network and select the local knowledge relationship chains that match the user operation behavior information; Step 4: Combine the selected local knowledge relationship chains to define a new preference knowledge relationship network for the user; Among them, in step 4, the new preference knowledge relationship network is composed of the closest preference knowledge relationship network plus several local knowledge relationship chains, and the new preference knowledge relationship network enters the database to upgrade the subsequent user feature description.

[0016] As a specific embodiment, in step three, the disassembled local knowledge relationship chain is matched with the user operation behavior information and the portrait, and the high similarity is used as the first description value, and the low similarity is used as the second description value.

[0017] As a specific embodiment, in step three, when the similarity of the disassembled local knowledge relationship chain is low, each local knowledge relationship chain in the preference knowledge relationship network associated with the local knowledge relationship chain continues to be matched with the user operation behavior information and portrait, and the high similarity is used as the second description value, and the low similarity is used as the third description value.

[0018] As a specific embodiment, in step four, if part of the user's operation behavior information exceeds the local knowledge relationship chain covered by the new preference knowledge relationship network, the new user operation behavior information enters step two, the user is re-characterized, and the new preference knowledge relationship network obtained covers a new preference knowledge relationship network.

[0019] An information optimization server includes a processor and a memory, the processor and the memory are communicatively connected, and the processor is used to read a computer program from the memory and execute it to implement the above method.

[0020] like Figure 2 As shown, as a specific embodiment, the processor includes a power module, the power module includes a power circuit, the power circuit includes an integrated circuit U1, a first capacitor C1, a second capacitor C2, a third capacitor C3, a fourth capacitor C4, a battery BT1, an electronic switch K1 and a diode VD1, the model of the integrated circuit U1 is 78L24, the input end of the integrated circuit U1 is grounded through the first capacitor C1 and the second capacitor C2 respectively, the output end of the integrated circuit U1 is grounded through the third capacitor C3 and the fourth capacitor C4 respectively, the ground end of the integrated circuit U1 is grounded, the input end of the integrated circuit U1 is electrically connected to the negative electrode of the battery BT1, the positive electrode of the battery BT1 is electrically connected to the output end of the integrated circuit U1 through the electronic switch K1, the trigger end of the electronic switch K1 is electrically connected to the cathode of the diode VD1, the anode of the diode VD1 is electrically connected to the output end of the integrated circuit U1, the electronic switch K1 is an IGBT, when the power circuit loses power, the internal circuit will generate a reverse voltage, thereby turning on the electronic switch K1 through the diode VD1, after the electronic switch K1 is turned on, the battery BT1 can continue to output the power supply voltage to ensure that the power circuit outputs the working voltage.

[0021] The above is based on the present invention as an inspiration. Through the above description, relevant staff can make various changes and modifications without departing from the technical idea of ​​this invention. The technical scope of this invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An information optimization method for artificial intelligence, characterized in that: Applied to the information optimization server, the optimization method comprises the following steps: Step 1: Obtain basic user information, where the basic information includes user operation behavior information corresponding to the cloud service interaction event and the user portrait of the cloud service interaction event; Step 2: Obtain the user preference knowledge relationship network, and select several corresponding preference knowledge relationship networks according to the user operation behavior information; Step 3: Disassemble the local knowledge relationship chains of each preference knowledge relationship network and select the local knowledge relationship chains that match the user operation behavior information; Step 4: Combine the selected local knowledge relationship chains to define a new preference knowledge relationship network for the user; Among them, in step 4, the new preference knowledge relationship network is composed of the closest preference knowledge relationship network plus several local knowledge relationship chains, and the new preference knowledge relationship network enters the database to upgrade the subsequent user feature description.

2. The information optimization method for artificial intelligence according to claim 1, characterized in that: In step three, the disassembled local knowledge relationship chain is matched with the user operation behavior information and the portrait, and the high similarity is used as the first description value, and the low similarity is used as the second description value.

3. The information optimization method for artificial intelligence according to claim 2, characterized in that: In step three, when the similarity of the disassembled local knowledge relationship chain is low, each local knowledge relationship chain in the preference knowledge relationship network associated with the local knowledge relationship chain continues to be matched with the user operation behavior information and portrait, and the high similarity is used as the second description value, and the low similarity is used as the third description value.

4. The information optimization method for artificial intelligence according to claim 1, characterized in that: In step 4, if part of the user's operation behavior information exceeds the local knowledge relationship chain covered by the new preference knowledge relationship network, the new user operation behavior information enters step 2, the user is re-characterized, and the new preference knowledge relationship network obtained covers the previous new preference knowledge relationship network.

5. An information optimization server, characterized in that: The invention comprises a processor and a memory, wherein the processor and the memory are communicatively connected, and the processor is used to read a computer program from the memory and execute it to implement the method described in any one of claims 1 to 4.

6. The information optimization server according to claim 5, characterized in that: The processor includes a power module, the power module includes a power circuit, the power circuit includes an integrated circuit, a first capacitor, a second capacitor, a third capacitor, a fourth capacitor, a battery, an electronic switch and a diode, the model of the integrated circuit is 78L24, the input end of the integrated circuit is grounded through the first capacitor and the second capacitor respectively, the output end of the integrated circuit is grounded through the third capacitor and the fourth capacitor respectively, the ground end of the integrated circuit is grounded, the input end of the integrated circuit is electrically connected to the negative electrode of the battery, the positive electrode of the battery is electrically connected to the output end of the integrated circuit through the electronic switch, the trigger end of the electronic switch is electrically connected to the cathode of the diode, the anode of the diode is electrically connected to the output end of the integrated circuit, and the electronic switch is an IGBT.

Images